Nishi Family › Compare › Autonomous Team and Software Agents

Nishi Compare · capabilities, evidence and delivery

Autonomous Team and Software Agents

Compare capabilities and delivery evidence. Source discovery, qualification, deployment and accepted outcomes are separate; an open contract names work still to verify.

Nishi vs SWE-agent and OpenHands and Aider and AutoGen

Overview

The purpose, declared position and evidence coverage of this domain. Source presence and completed acceptance are different measures.

Where we are. Measured 2026-08-19. The team is a real governance-and-verification shell -- zero-token execute-and-verify loop, anti-drift coach, heartbeat boards, governed pulses, lineage, honest autonomy metering, refusal over fabrication -- and the 2026-07-05 diagnosis still stands: it is not a builder. The forge lane (local Coder seat with a byte-exact judge, measured 0 of 3) is the incumbent for authoring and is now named on the headline row; SWE-bench Verified ingest and grading exist for the issue-to-patch rung; the container host exists for the sandbox.

Where we need to go. Give real workstreams machine-executable targets, move authoring off the zero floor under the coach and gates the shell already provides, then repo loops, governance UX and agents -- the governance the field lacks wrapped around the authorship we lack. OPERATOR SCOPE 2026-09-07: pointing the team at a domain should initiate evidence-backed evaluation, a dependency roadmap, bounded experiments on algorithms and complexity, independent verification and repeatable results, with findings fed back into the roadmap. The unstructured -> structured -> meaningful -> actionable -> reproducible pipeline applies throughout; LLM interpretations retain uncertainty and provenance.

The unit. 1 u = one measured session-leg. Calibration from landed rungs: the mangagen panel compositor went from existing substrate to shipped and live-verified in ONE leg (2026-08-13); the citations rung went from 3 to 55 domains in one leg across seven seats (2026-08-18); a greenfield engine with a bite-proven gate has measured 2 to 4 legs. Estimates recalibrate as rungs land and PR7 actuals write back.
Cost to targets and authoring: 3 u. Through M0.
Cost to repo loops: 8 u. Through M1.
Cost to agents: 14 u. Everything below.

Latest recorded release

No valid dated release entry is recorded for this domain.

Release entries describe recorded changes; they do not establish that every capability passed evaluation.

10 of 20 capability source symbols found|2 of them authored stronger-claims|10 open|coverage 500/1000|adoption 4 full / 6 partial

Evidence profile — what the gaps on this board actually are

Measured by nx_swcompare_evidence, read back by nx_evprofile_lib. Every figure is a count with its denominator — there is deliberately no score, no grade and no percentage anywhere in this band, because a stored scalar is a field a seat can edit and a counted partition is not.

evidence|grounded 10/10|unsupported 0|gates green 1/1|proven able to fail 0/1|never bitten 1|green at 0/0 0|open gaps 10|of them unnamed 0|of them proof withheld 0|flips ready 0

proven able to fail counts the gates that have a RECORDED RED — nx_gate_bite mutated the gate subject, rebuilt it, watched the gate go red, and that record is inside the shared TTL. never bitten is its complement over the same denominator: those gates ran and were green, and nothing has ever shown them able to detect anything, so their green is a statement about this run and not about the gate. green at 0/0 is a separate and much weaker observation — the gate printed GREEN on a zero denominator, so its own tooth counter says it examined nothing. A gate can be green, non-zero, and still never bitten; that is the common case and it is now visible instead of implied.

partition: grounded + unsupported = 10 vs present 10 · named + unnamed + withheld = 10 vs open 10 · both reconcile

liar-kill conj=GPQN · all four conjuncts held

graded document: BUILDROOT tree, 6733 bytes · gates map: PRIMARY · stamped 1d 7h ago · source ../knowledge/status/evstamp_team.verdict

Gap classWhat it is, and the work it names
NONENo gap class fires on this board: every published claim is grounded, the declared gates ran and were green, no watch contract is unnamed or already landed, and the stamp is inside its TTL. That is a statement about evidence, not about depth, scale or polish.
This band reports the referee counts. The per-axis worklist rows — which axis is unsupported, which watch is ready to flip, which gap is unnamed — are printed by nx_swcompare_evidence team itself and are not carried on the stamp, so this page names the classes and the producer names the rows. That split is stated rather than hidden: a count without a worklist is not actionable, and this band is honest about which half of that it is.

Production map

Follow the dependencies, declared acceptance criteria and recorded priorities. Inspect source binding before treating a rank as executable work.

Ranking source binding: STALE_OR_INVALID_BINDING. Recorded priorities require current acceptance evidence and resource checks before execution.

Recorded ranking withheld

Retained ranking is not bound to the current plan and matrix: STALE_OR_INVALID_BINDING. Historical data remains retained. Refresh the ranking after resolving the input differences. Latest execution outcome is unverified.

Declared roadmap — contract, acceptance, executor, effort

RungCloses withDefinition of done (pre-declared)ExecutorEst.
Machine-executable targets on real workstreams (R0)ee_target_declareStalled workstreams declare a target row (gate or bench plus accept rule) the exec engine can run; the engine's own coverage line moves from 0 of 104 and the number is the proof. Proposed responsibility model, NOT claimed implemented or enforced: PM accountable for delivery and sequencing; engineer responsible for implementation and experiment artifacts; independent referee verifies outcomes and reproducibility; operator retains authority over scope and consequential decisions; legal or domain review is consulted when the task requires it. Every data transition and task names its owner, provenance, output artifact, uncertainty and acceptance test. Acceptance requires a real completed workstream trace, including failure recovery, rather than role-directory counts.Organ1 u
Forge authoring past the zero floor (R1)
after R0		fe_author_organThe local forge cascade authors a novel organ that compiles, runs and passes its declared gate; nx_forge_local_bench moves from 0 of 3 by a PRE-DECLARED floor and the floor ratchetsLocal model2 u
Issue-to-patch over SWE-bench Verified (R2)
after R1		ip_resolveThe forge loop resolves banked SWE-bench Verified instances (the swebv ingest and grader already exist) end to end; pass rate published beside the field's, never claimed above itOrgan2 u
Git-native pair loop (R3)
after R1		gp_editRepo map, diff-style edits and auto-commit over the sovereign git; a planted failing test is fixed by the loop and committed with the gate's evidenceOrgan1.5 u
Sandbox per task (R4)as_spawnEach agent task runs in the container host the containers domain already ships, with the ocap grant of the swarm; escape attempts in the fixture are refusedOrgan1.5 u
Human-in-the-loop approvals (R5)th_approveDENY-WINS approvals from the workflow domain gate every external action of an agent; the approval is a recorded rowOrgan1 u
Agent memory (R6)am_recallPer-agent memory stream with recall over it (nx_charmem and em_recall are the substrate); a planted false memory is refutable by the reflection primitiveOrgan1 u
Multi-agent conversation (R7)
after R6		ac_turnTwo or more sovereign-seat agents converse through the conductor with turn budgets; the transcript is additive and replayable; outcome graded by the referee. Proposed research collaboration responsibilities include generation, reflection, ranking, evolution and independent meta-review, admitted only after comparison with the candidate research oracles on ecosystem EC42. The transcript must show who proposed, who implemented and who independently verified; autonomous completion needs a reproducible artifact and a referee verdict, not agreement between agents.Local model2 u
Agent session UI (R8)au_pageLive agent sessions on the portal with the board's liveness semantics; a stalled session reads STALLED, never ACTIVEOrgan1.5 u
Budget meter (R9)ab_meterTokens, wall time and any external spend metered per session as rows; the zero-token loop reads zero, which is the point. Scope clarification 2026-09-07: join session metering to engineshift ES18 total cost per verified result, including local and remote tokens/context, retries, review, autonomous completions, interventions, recurrence and recovery. Preserve missing-data states and denominator coverage; a shorter conversation is not sufficient evidence of better delivery.Organ0.5 u

Milestones

MilestoneRungsCumulative
M0 · Targets and authoringR0,R13 u
M1 · Repo loopsR2,R3,R48 u
M2 · Governance UXR5,R8,R911 u
M3 · AgentsR6,R714 u
Ladder verdict. NOT DECLARED. This board names no dated best-in-class or frontier target and no rung roles (sotatarget and rungrole rows on its plan); the ranker labels it NO-LADDER until it does, and until then its rungs climb toward a target nobody has written down. Bars read NO-BAR against the current month 2026-10.
Bar freshness, counted
ClassCountNote
bars0sotabar rows on the plan
fresh0the bar month is the current month
attested0an older bar with a this-month barscan reporting no newer entry
stale0a this-month scan saw a newer month the bar ignores
unattested0nobody looked this month
malformed0a sotabar row missing a field
duplicate0bar ids an earlier row already carries
bars, summed0RECONCILED: the parts sum to the total 0
current month2026-10the month every bar is judged against
Treatment verdict. NOT DECLARED. No rung on this board declares its three-step treatment (a treat row naming the MCP row, the API route, the primitive it composes, the workflow that composes it and the agent beat that runs it); the ranker labels every rung TREATMENT-UNDECLARED until it does.

Inspect a rung and its prerequisites

Declared nodes 10. Rank input binding: STALE_OR_INVALID_BINDING. Dependency order is authored. Implementation, acceptance evidence, authority and resource readiness are unverified. No action is recommended or dispatched here.

Plan SHA-256 588122aa3b2b92a9e9f3a5257f99def98b99ac3d60605b11ac262f93d865b302. Target rows 0; role rows 0. Existing risks and release worklog retain their own scope; no node completion is inferred.

Runtime observation coverage: 0 of 10 rungs have current, identity-bound execution observations. Observation may report RED. Accepted completion remains unknown; source presence, qualification and deployment do not establish it.

Use Enter or Space on a rung to inspect its contract. Prerequisite links locate another rung in this list; open its summary to inspect it. Estimates are authored effort, not forecasts.

  1. R0 — Machine-executable targets on real workstreams

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: ee_target_declare

    Acceptance: Stalled workstreams declare a target row (gate or bench plus accept rule) the exec engine can run; the engine's own coverage line moves from 0 of 104 and the number is the proof. Proposed responsibility model, NOT claimed implemented or enforced: PM accountable for delivery and sequencing; engineer responsible for implementation and experiment artifacts; independent referee verifies outcomes and reproducibility; operator retains authority over scope and consequential decisions; legal or domain review is consulted when the task requires it. Every data transition and task names its owner, provenance, output artifact, uncertainty and acceptance test. Acceptance requires a real completed workstream trace, including failure recovery, rather than role-directory counts.

    Authored effort: 1. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  2. R1 — Forge authoring past the zero floor

    Prerequisites: R0 (acceptance unverified)

    Contract: fe_author_organ

    Acceptance: The local forge cascade authors a novel organ that compiles, runs and passes its declared gate; nx_forge_local_bench moves from 0 of 3 by a PRE-DECLARED floor and the floor ratchets

    Authored effort: 2. Executor kind: Local model. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  3. R2 — Issue-to-patch over SWE-bench Verified

    Prerequisites: R1 (acceptance unverified)

    Contract: ip_resolve

    Acceptance: The forge loop resolves banked SWE-bench Verified instances (the swebv ingest and grader already exist) end to end; pass rate published beside the field's, never claimed above it

    Authored effort: 2. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  4. R3 — Git-native pair loop

    Prerequisites: R1 (acceptance unverified)

    Contract: gp_edit

    Acceptance: Repo map, diff-style edits and auto-commit over the sovereign git; a planted failing test is fixed by the loop and committed with the gate's evidence

    Authored effort: 1.5. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  5. R4 — Sandbox per task

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: as_spawn

    Acceptance: Each agent task runs in the container host the containers domain already ships, with the ocap grant of the swarm; escape attempts in the fixture are refused

    Authored effort: 1.5. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  6. R5 — Human-in-the-loop approvals

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: th_approve

    Acceptance: DENY-WINS approvals from the workflow domain gate every external action of an agent; the approval is a recorded row

    Authored effort: 1. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  7. R6 — Agent memory

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: am_recall

    Acceptance: Per-agent memory stream with recall over it (nx_charmem and em_recall are the substrate); a planted false memory is refutable by the reflection primitive

    Authored effort: 1. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  8. R7 — Multi-agent conversation

    Prerequisites: R6 (acceptance unverified)

    Contract: ac_turn

    Acceptance: Two or more sovereign-seat agents converse through the conductor with turn budgets; the transcript is additive and replayable; outcome graded by the referee. Proposed research collaboration responsibilities include generation, reflection, ranking, evolution and independent meta-review, admitted only after comparison with the candidate research oracles on ecosystem EC42. The transcript must show who proposed, who implemented and who independently verified; autonomous completion needs a reproducible artifact and a referee verdict, not agreement between agents.

    Authored effort: 2. Executor kind: Local model. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  9. R8 — Agent session UI

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: au_page

    Acceptance: Live agent sessions on the portal with the board's liveness semantics; a stalled session reads STALLED, never ACTIVE

    Authored effort: 1.5. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

  10. R9 — Budget meter

    Prerequisites: None declared; this does not establish execution eligibility.

    Contract: ab_meter

    Acceptance: Tokens, wall time and any external spend metered per session as rows; the zero-token loop reads zero, which is the point. Scope clarification 2026-09-07: join session metering to engineshift ES18 total cost per verified result, including local and remote tokens/context, retries, review, autonomous completions, interventions, recurrence and recovery. Preserve missing-data states and denominator coverage; a shorter conversation is not sufficient evidence of better delivery.

    Authored effort: 0.5. Executor kind: Organ. Responsible, accountable and verifier not established. Inspect retained worklog.

    Runtime observation: UNKNOWN; outcome UNKNOWN; observed epoch -1. Declared owner: . Receipt , SHA-256 . Identity-bound observation is not accepted completion. Qualification and deployment remain unverified by this projection.

Learning and practice paths

No structured learning path is declared for this plan. Existing research, roadmap and worklog remain available above.

Rung dossiers — every record that bears on a rung, in one place

Joined by symbol, never typed. Each dossier is assembled on every publish from the rows this board already carries: the plan's rung row, the matrix row that carries its contract symbol (its status re-measured by the one symbol ruler), the gate the organ declares and the verdict the evidence referee recorded on its last run, the reference marks in the rung text, the design rows that name the rung and the work log filed against it. The capability matrix links each cell to its dossier and each dossier links back to its cell and forward to the rungs it stands on; a dependency naming no rung on this plan is written as UNRESOLVED rather than linked. Absences are named: NO-MATRIX-ROW, NO-GATE-DECLARED, UNRECORDED.
Gate verdicts: UNSTAMPED — no per-gate verdict artifact is published for this domain yet (nx_swcompare_evidence team writes it beside its stamp); every gate below reads UNRECORDED until it runs.
Gate declarations: knowledge/organ_gate.conf read from this working directory (1 rows) and from the estate root (196 rows); rows in both counted once: 0; declarations read: 197. Every declaration in either copy counts, so a stub beside the publisher can never hide the root.
R0 Machine-executable targets on real workstreams · cell WATCHING · gate NO-GATE-DECLARED
Contractee_target_declare · executor Organ · 1 u · stands on nothing
Definition of doneStalled workstreams declare a target row (gate or bench plus accept rule) the exec engine can run; the engine's own coverage line moves from 0 of 104 and the number is the proof. Proposed responsibility model, NOT claimed implemented or enforced: PM accountable for delivery and sequencing; engineer responsible for implementation and experiment artifacts; independent referee verifies outcomes and reproducibility; operator retains authority over scope and consequential decisions; legal or domain review is consulted when the task requires it. Every data transition and task names its owner, provenance, output artifact, uncertainty and acceptance test. Acceptance requires a real completed workstream trace, including failure recovery, rather than role-directory counts.
Matrix cellMachine-executable targets on stalled workstreams · runtime/nx_exec_engine.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_exec_engine; declare nx_exec_engine TAB <gate> and the ship loop proves it and the verdict lands here.
Work log2026-09-07 queue OPERATOR SCOPE 2026-09-07: domain-to-evaluation-to-roadmap-to-experiments-to-reproducible-evidence autonomy is requested. Responsibility assignments are PROPOSED, not mechanically enforced: PM delivery accountability, engineer implementation, independent referee verification, operator authority and applicable legal/domain consultation. Meaning-making remains LLM-assisted interpretation with independent verification. This is requested work, not completed autonomy.
R1 Forge authoring past the zero floor · cell WATCHING · gate NO-GATE-DECLARED
Contractfe_author_organ · executor Local model · 2 u · stands on R0
Definition of doneThe local forge cascade authors a novel organ that compiles, runs and passes its declared gate; nx_forge_local_bench moves from 0 of 3 by a PRE-DECLARED floor and the floor ratchets
Matrix cellLLM-driven code authoring (novel organ building) · runtime/nx_forge_engine.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_forge_engine; declare nx_forge_engine TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R2 Issue-to-patch over SWE-bench Verified · cell WATCHING · gate NO-GATE-DECLARED
Contractip_resolve · executor Organ · 2 u · stands on R1
Definition of doneThe forge loop resolves banked SWE-bench Verified instances (the swebv ingest and grader already exist) end to end; pass rate published beside the field's, never claimed above it
Matrix cellIssue-to-patch repository pipeline · runtime/nx_issue_patch.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_issue_patch; declare nx_issue_patch TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R3 Git-native pair loop · cell WATCHING · gate NO-GATE-DECLARED
Contractgp_edit · executor Organ · 1.5 u · stands on R1
Definition of doneRepo map, diff-style edits and auto-commit over the sovereign git; a planted failing test is fixed by the loop and committed with the gate's evidence
Matrix cellGit-native pair-programming edit loop · runtime/nx_git_pair.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_git_pair; declare nx_git_pair TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R4 Sandbox per task · cell WATCHING · gate NO-GATE-DECLARED
Contractas_spawn · executor Organ · 1.5 u · stands on nothing
Definition of doneEach agent task runs in the container host the containers domain already ships, with the ocap grant of the swarm; escape attempts in the fixture are refused
Matrix cellSandboxed per-task agent runtime · runtime/nx_agent_sandbox.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_agent_sandbox; declare nx_agent_sandbox TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R5 Human-in-the-loop approvals · cell WATCHING · gate NO-GATE-DECLARED
Contractth_approve · executor Organ · 1 u · stands on nothing
Definition of doneDENY-WINS approvals from the workflow domain gate every external action of an agent; the approval is a recorded row
Matrix cellHuman-in-the-loop approval flows · runtime/nx_team_hitl.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_team_hitl; declare nx_team_hitl TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R6 Agent memory · cell WATCHING · gate NO-GATE-DECLARED
Contractam_recall · executor Organ · 1 u · stands on nothing
Definition of donePer-agent memory stream with recall over it (nx_charmem and em_recall are the substrate); a planted false memory is refutable by the reflection primitive
Matrix cellLong-horizon planning and memory for agents · runtime/nx_agent_memory.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_agent_memory; declare nx_agent_memory TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R7 Multi-agent conversation · cell WATCHING · gate NO-GATE-DECLARED
Contractac_turn · executor Local model · 2 u · stands on R6
Definition of doneTwo or more sovereign-seat agents converse through the conductor with turn budgets; the transcript is additive and replayable; outcome graded by the referee. Proposed research collaboration responsibilities include generation, reflection, ranking, evolution and independent meta-review, admitted only after comparison with the candidate research oracles on ecosystem EC42. The transcript must show who proposed, who implemented and who independently verified; autonomous completion needs a reproducible artifact and a referee verdict, not agreement between agents.
Matrix cellMulti-agent conversation framework · runtime/nx_agent_chat.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_agent_chat; declare nx_agent_chat TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R8 Agent session UI · cell WATCHING · gate NO-GATE-DECLARED
Contractau_page · executor Organ · 1.5 u · stands on nothing
Definition of doneLive agent sessions on the portal with the board's liveness semantics; a stalled session reads STALLED, never ACTIVE
Matrix cellWeb UI for agent sessions · runtime/nx_agent_ui.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_agent_ui; declare nx_agent_ui TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet
R9 Budget meter · cell WATCHING · gate NO-GATE-DECLARED
Contractab_meter · executor Organ · 0.5 u · stands on nothing
Definition of doneTokens, wall time and any external spend metered per session as rows; the zero-token loop reads zero, which is the point. Scope clarification 2026-09-07: join session metering to engineshift ES18 total cost per verified result, including local and remote tokens/context, retries, review, autonomous completions, interventions, recurrence and recovery. Preserve missing-data states and denominator coverage; a shorter conversation is not sufficient evidence of better delivery.
Matrix cellCost and token budget management · runtime/nx_agent_budget.nx · WATCHING decl
GateNO-GATE-DECLARED — knowledge/organ_gate.conf carries no row for nx_agent_budget; declare nx_agent_budget TAB <gate> and the ship loop proves it and the verdict lands here.
Work logno log row names this rung yet

dossiers=10 cells_joined=10 no_matrix_row=0 (sum 10) gates_recorded=0 gates_unrecorded=0 no_gate_declared=10 (sum 10 of cells_joined) evgates=UNSTAMPED

Capability comparisons

Compare the field, search individual capabilities and open their source and adoption evidence. Documented presence does not establish comparative quality.

Position map — centrality and distinctiveness

The four-quadrant map the field uses for brand strategy (Dawar and Bagga, HBR June 2015), re-derived from this matrix on every publish. Centrality is the share of the category's feature mass a player covers, each feature weighted by how many hold it; distinctiveness is the average lead over each rival on the rows the player holds; breadth is the depth-weighted share of the whole matrix (the bubble); depth is how deeply the rows held are held; momentum is the day-over-day move off the spine (green rising, red falling, grey until day two); the dashed path runs first day → previous day → today. Dividers are the category means. Axes are fitted to the field of play, so read the tick numerals, not the frame. Rival marks are documented presence, so a rival's position reads the record, never its quality. The picture grades its own readability below; the table beside it is the same data for a screen reader or a second method.

Rows. 20 feature rows mapped of 20 matrix rows; 0 substrate rows (kernels, bounds and instruments the plan's rungrole marks substrate) are the estate's scaffolding, not category features, and stay off the map
Views. 2D cut: centrality, distinctiveness · 3D cube: centrality, distinctiveness, breadth · axes registered: centrality, distinctiveness, breadth, depth, momentum · a board picks its own in knowledge/compare/team.cdmap (cut|x|y, cube|x|y|z); absent = the HBR defaults
Position map, two-dimensional cutOne bubble per player. Bubble area is breadth, the ring colour is momentum, the dashed lines are the category means, and both axes are fitted to the field of play with their tick numerals shown. Every value is repeated in the table that follows. 300 400 500 600 700 800 900 1000 100 200 300 400 500 600 700 centrality (permil, fitted 300–1000) distinctiveness (permil, fitted 100–700) mean 685 mean 318 Unconventional Aspirational Peripheral Mainstream Nishi, centrality 410, distinctiveness 575, breadth 366, depth 733, momentum 0 SWE-agent, centrality 696, distinctiveness 233, breadth 300, depth 600, momentum 0 OpenHands, centrality 875, distinctiveness 345, breadth 450, depth 642, momentum 0 Aider, centrality 642, distinctiveness 203, breadth 266, depth 592, momentum 0 AutoGen, centrality 803, distinctiveness 237, breadth 333, depth 512, momentum 0 Nishi SWE-agent OpenHands Aider AutoGen

bubble area = breadth · ring = momentum (green rising, red falling, grey until day two) · dashed = category means · axes fitted to the field of play: centrality 300–1000, distinctiveness 100–700 of 0–1000 permil (the full range put every player in one corner)
readability of the 2D cut, self-graded by the layout ruler: label overlaps 0 · labels over marks 0 · off-canvas 0 · unresolved labels 0 · mark overlaps 0 (a fact of the data: two players that close are that close) · data spread 642 permil of the plot · quadrant words unseated 0
text contrast, measured with wcag2-ratio (floors from contrast.conf), light theme: labels 16.24 (floor 4.50) · notes 16.24 (floor 4.50) · quadrant words 5.89 (floor 4.50) · tick numerals 5.89 (floor 4.50) · axis titles 5.59 (floor 4.50) · dark theme: labels 13.78 (floor 4.50) · quadrant words 5.55 (floor 4.50) · axis titles 5.97 (floor 4.50) · dark classes under their floor 0 (one figure serves both themes: a dark shortfall is a token to fix, never a class to hide) · classes refused under their floor 0 (a refused class is not drawn; the scale classes are measured, never hidden) · export: SVG PNG (receipt, rendered by the estate's own rasteriser from this page)
Position map, three-dimensional cubeThe same players in an isometric cube. Each axis is fitted to its own field of play and carries numerals on the floor grid and the vertical axis; each bubble drops a dotted line to its floor shadow so height reads as height. Values are in the table that follows. 300 400 500 600 700 800 900 1000 100 200 300 400 500 600 700 200 250 300 350 400 450 500 centrality distinctiveness breadth Aider: centrality 642, distinctiveness 203, breadth 266 SWE-agent: centrality 696, distinctiveness 233, breadth 300 AutoGen: centrality 803, distinctiveness 237, breadth 333 Nishi: centrality 410, distinctiveness 575, breadth 366 OpenHands: centrality 875, distinctiveness 345, breadth 450 Nishi SWE-agent OpenHands Aider AutoGen
axes fitted: centrality 300–1000 · distinctiveness 100–700 · breadth 200–500 permil · farther bubbles are painted first, nearer ones over them · the floor shadow is each bubble's (x, y) at height 0
readability of the 3D cube, self-graded by the layout ruler: label overlaps 0 · labels over marks 0 · off-canvas 0 · unresolved labels 0 · mark overlaps 1 (a fact of the data: two players that close are that close) · data spread 363 permil of the plot
Position map, small multiplesEvery pair of registered axes as one small cut. Each panel fits both axes to the field of play, the dashed lines are the category means, bubble area is breadth and the ring colour is momentum; the legend below names the colours. 300 1000 100 700 distinctiveness vs centrality Nishi: centrality 410, distinctiveness 575 SWE-agent: centrality 696, distinctiveness 233 OpenHands: centrality 875, distinctiveness 345 Aider: centrality 642, distinctiveness 203 AutoGen: centrality 803, distinctiveness 237 300 1000 200 500 breadth vs centrality Nishi: centrality 410, breadth 366 SWE-agent: centrality 696, breadth 300 OpenHands: centrality 875, breadth 450 Aider: centrality 642, breadth 266 AutoGen: centrality 803, breadth 333 300 1000 450 800 depth vs centrality Nishi: centrality 410, depth 733 SWE-agent: centrality 696, depth 600 OpenHands: centrality 875, depth 642 Aider: centrality 642, depth 592 AutoGen: centrality 803, depth 512 300 1000 480 520 momentum vs centrality Nishi: centrality 410, momentum 500 SWE-agent: centrality 696, momentum 500 OpenHands: centrality 875, momentum 500 Aider: centrality 642, momentum 500 AutoGen: centrality 803, momentum 500 100 700 200 500 breadth vs distinctiveness Nishi: distinctiveness 575, breadth 366 SWE-agent: distinctiveness 233, breadth 300 OpenHands: distinctiveness 345, breadth 450 Aider: distinctiveness 203, breadth 266 AutoGen: distinctiveness 237, breadth 333 100 700 450 800 depth vs distinctiveness Nishi: distinctiveness 575, depth 733 SWE-agent: distinctiveness 233, depth 600 OpenHands: distinctiveness 345, depth 642 Aider: distinctiveness 203, depth 592 AutoGen: distinctiveness 237, depth 512 100 700 480 520 momentum vs distinctiveness Nishi: distinctiveness 575, momentum 500 SWE-agent: distinctiveness 233, momentum 500 OpenHands: distinctiveness 345, momentum 500 Aider: distinctiveness 203, momentum 500 AutoGen: distinctiveness 237, momentum 500 200 500 450 800 depth vs breadth Nishi: breadth 366, depth 733 SWE-agent: breadth 300, depth 600 OpenHands: breadth 450, depth 642 Aider: breadth 266, depth 592 AutoGen: breadth 333, depth 512 200 500 480 520 momentum vs breadth Nishi: breadth 366, momentum 500 SWE-agent: breadth 300, momentum 500 OpenHands: breadth 450, momentum 500 Aider: breadth 266, momentum 500 AutoGen: breadth 333, momentum 500 450 800 480 520 momentum vs depth Nishi: depth 733, momentum 500 SWE-agent: depth 600, momentum 500 OpenHands: depth 642, momentum 500 Aider: depth 592, momentum 500 AutoGen: depth 512, momentum 500
Nishi SWE-agent OpenHands Aider AutoGen
10 panels over 5 registered axes, every pair once (the lower axis on x, the higher on y) · each panel fitted to its own field of play, first and last tick numerals shown · no labels in a small cut, the legend names the colours; the grade below reports the mark terms only (MM summed over the panels, spread averaged)
readability of the small multiples, self-graded by the layout ruler: label overlaps 0 · labels over marks 0 · off-canvas 0 · unresolved labels 0 · mark overlaps 2 (a fact of the data: two players that close are that close) · data spread 504 permil of the plot
PlayerQuadrantcentralitydistinctivenessbreadthdepthmomentumRows heldDays on spineFirst seen
NishiUnconventional4105753667330 since 2026-09-2310102026-09-15
SWE-agentMainstream6962333006000 since 2026-09-2310102026-09-15
OpenHandsAspirational8753454506420 since 2026-09-2314102026-09-15
AiderPeripheral6422032665920 since 2026-09-239102026-09-15
AutoGenMainstream8032373335120 since 2026-09-2313102026-09-15
DayMatrix rows reviewedPlayers recorded
2026-09-15205
2026-09-16205
2026-09-17205
2026-09-18205
2026-09-19205
2026-09-20205
2026-09-21205
2026-09-22205
2026-09-23205
2026-10-08205

players 5|matrix rows 20|feature mass 56|centrality mean 685|distinctiveness mean 318|axes 5|spine days 10 (shown 10)|rows written today 0|readability defects 2D 0 cube 0|spine knowledge/status/cdmap/team.spine

How to read this evidence. A Nishi source mark records whether the named symbol is declared in the selected source file. It does not establish working behavior or accepted delivery. A watching tag names an expected source entry; discovering it updates source coverage only. A dark tag means the file exists but the named symbol was not found: inspect the source and contract before assuming the capability is missing or renaming code. Peer codes are authored assessments; unassessed means no comparison is established, not absence. Qualification, deployment identity, runtime observations and acceptance must carry their own evidence. Adoption records the catalog's observed path through source, build, promotion, registration and invocation; libraries use importer evidence and gates use declared execution surfaces. A full catalog path does not establish quality, freshness or a successful user outcome. Partial and unknown states retain their stated next action. Census stamps: importers asof 1790637268, gate census asof 1790104131 (unix seconds; -1 = census absent).

Capability matrix — measured against source

◉ authored stronger claim; source present● present◐ partial○ absent? unassessed; excluded from relative comparison · click any capability for its evidence

Peer cell coverage: authored assessed 80, unassessed 0. Authored assessments are not verified outcomes.

CapabilityNishiSWE-agentOpenHandsAiderAutoGen
Autonomous execute-and-verify loop on machine targetsMeasured: run_tool exists in runtime/nx_exec_engine.nx, verified at emit. LIVE-gated 2026-07-06: 3/3 targets advanced (2 evo-synth held-out + compiler-health witness); its own output prints the honest coverage: 0 of 104 stalled workstreams declare a machine-executable target yet rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them Adoption: BUILT-UNPROMOTED — PARTIAL: compiled, never promoted to the serving root: /api/promote it.
not adopted: compiled, never promoted to the serving root: /api/promote it
Pros Implementing source symbol found; runtime acceptance separateCons behind OpenHands (leads); not adopted yet: compiled, never promoted to the serving root: /api/promote it
●●◉●●
Anti-drift coach gating rung claims (liar-killer)Measured: wc_count exists in runtime/_hdl_build/nx_ws_coach.nx, verified at emit. Gate GREEN then census then coach; only COACH-OK claims a rung -- checks U-axes, dated bars, claim-vs-proof ratio, freshness; no field agent gates its own success claims against measured censuses Adoption: BUILT-UNPROMOTED — PARTIAL: compiled, never promoted to the serving root: /api/promote it.
not adopted: compiled, never promoted to the serving root: /api/promote it
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider, AutoGenCons not adopted yet: compiled, never promoted to the serving root: /api/promote it
●○○○○
Work board with heartbeat livenessMeasured: wb_count_ids exists in runtime/_hdl_build/nx_ws_board.nx, verified at emit. The board refuses to trust a stale ACTIVE label (imports nx_heartbeat_str, wellformed-checked); OpenHands and AutoGen track task state without staleness refusal [openhands-repo] Adoption: BUILT-UNPROMOTED — PARTIAL: compiled, never promoted to the serving root: /api/promote it.
not adopted: compiled, never promoted to the serving root: /api/promote it
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider, AutoGenCons not adopted yet: compiled, never promoted to the serving root: /api/promote it
●○◐○◐
Governed scheduler (warden-owned conductor pulses)Measured: cr_seed exists in runtime/_hdl_build/nx_conductor_registry.nx, verified at emit. Ratchet and training pulses run ONLY governed, never ad-hoc; AutoGen is the orchestration-framework bar [autogen2023] Adoption: LIB-WIRED importers=5 nonval=4 — fully adopted (top of its ladder).
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider; fully adopted on the estate ladderCons behind AutoGen (leads)
●○○○◉
Organ lineage genealogistMeasured: gen_register exists in runtime/_hdl_build/nx_genealogist.nx, verified at emit. Ancestry and relatedness of organs tracked as data; the field tracks conversation history, not artifact lineage Adoption: LIB-WIRED importers=4 nonval=1 — fully adopted (top of its ladder).
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider, AutoGen; fully adopted on the estate ladderCons none on the measured axes (rival marks are documented presence, not depth)
●○○○○
Honest autonomy meteringMeasured: am_read exists in runtime/_hdl_build/nx_autonomy_meter.nx, verified at emit. Measures the Claude-touch bar toward 0 -- the team scores its OWN dependence honestly; no field agent measures its own autonomy. 07-15 LIVING: nx_zero_claude_ledger persists the local-vs-Claude lift trend (0.5B 38%->1.5B 53% zero-token, sound because the LCF-kernel verifier only certifies correct answers) + the hybrid cascade routes local-first, escalates only the residual to the lightest Claude Adoption: RUN-BY:clock — fully adopted (top of its ladder).
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider, AutoGen; fully adopted on the estate ladderCons none on the measured axes (rival marks are documented presence, not depth)
●○○○○
Teacher and practice loopMeasured: tch_can_advance exists in runtime/nx_teacher.nx, verified at emit. Toy-practice honest (the 07-05 diagnosis); OpenHands and AutoGen have tutorial-ish agent training flows; NOTE this organ is one of the 19 live shadow-name collisions (runtime + _hdl_build copies differ) rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them Adoption: LIB-WIRED importers=6 nonval=3 — fully adopted (top of its ladder).
Pros Implementing source symbol found; runtime acceptance separate; ahead of SWE-agent, OpenHands, Aider, AutoGen; fully adopted on the estate ladderCons none on the measured axes (rival marks are documented presence, not depth)
●○◐○◐
LLM-driven code authoring (novel organ building)DARK — runtime/nx_forge_engine.nx EXISTS but does not declare fe_author_organ: something shipped at this path under another name, and this mark would read open forever. Repoint the contract to the real entry point (the plan rung AND this row) or rename the function; the flip follows on the next beat, and the comparewatch- plane row reads DARK until then. THE headline absent: every novel organ falls to Claude (diagnosis 2026-07-05, unchanged today); LLM code-authorship is the field's entire product rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching fe_author_organ
Pros none measured yetCons behind SWE-agent, OpenHands (leads), Aider, AutoGen; open contract; expected source declaration not established
○●◉●●
Issue-to-patch repository pipelineOpen — watching runtime/nx_issue_patch.nx : ip_resolve, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. SWE-agent was born from SWE-bench issue resolution [sweagent2024]
dossierwatching ip_resolve
Pros none measured yetCons behind SWE-agent (leads), OpenHands, Aider; open contract; expected source declaration not established
○◉●●○
Git-native pair-programming edit loopOpen — watching runtime/nx_git_pair.nx : gp_edit, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. Aider is the bar: repo-map + diff edits + auto-commit [aider]
dossierwatching gp_edit
Pros none measured yetCons behind SWE-agent, OpenHands, Aider (leads); open contract; expected source declaration not established
○●●◉○
Sandboxed per-task agent runtimeOpen — watching runtime/nx_agent_sandbox.nx : as_spawn, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. OpenHands docker runtime is the bar [openhands2024]; our container host exists as a SEPARATE domain (950/1000) but is not wired under the team [sweagent-repo]
dossierwatching as_spawn
Pros none measured yetCons behind SWE-agent, OpenHands (leads), AutoGen; open contract; expected source declaration not established
○◐◉○◐
Multi-agent conversation frameworkOpen — watching runtime/nx_agent_chat.nx : ac_turn, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. AutoGen is the bar; our conductor schedules pulses, it does not orchestrate agent dialogue rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching ac_turn
Pros none measured yetCons behind OpenHands, AutoGen (leads); open contract; expected source declaration not established
○○◐○◉
Long-horizon planning and memory for agentsOpen — watching runtime/nx_agent_memory.nx : am_recall, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. Hot frontier axis; our WMS registry and memory files serve Claude, not the team organs rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching am_recall
Pros none measured yetCons behind SWE-agent, OpenHands, Aider, AutoGen; open contract; expected source declaration not established
○◐◐◐◐
Benchmark-scored coding evaluationMeasured: lb_one exists in runtime/nx_forge_local_bench.nx, verified at emit. 07-15 NOW PRESENT: nx_forge_local_bench scores the local Coder-0.5B via nx_forge_judge BYTE-EXACT compile+run (provable GREEN, exceeds flaky-test verifiers) -- MEASURED 0/3 honest floor (candidates compile+run, bytes differ). We HAVE the objective grader + a real number; SWE-bench pass-rate is the field bar [swebench2023] and we are far behind (present, not best) Adoption: SOURCE-ONLY — PARTIAL: source exists, never compiled: /api/build it.
not adopted: source exists, never compiled: /api/build it
Pros Implementing source symbol found; runtime acceptance separate; ahead of OpenHands, Aider, AutoGenCons behind SWE-agent (leads); not adopted yet: source exists, never compiled: /api/build it
●◉◐◐◐
Human-in-the-loop approval flowsOpen — watching runtime/nx_team_hitl.nx : th_approve, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. Operator gating exists by DOCTRINE and the workflow domain ships DENY-WINS approvals, but no team organ carries approval flows [autogen-repo]
dossierwatching th_approve
Pros none measured yetCons behind SWE-agent, OpenHands, Aider, AutoGen; open contract; expected source declaration not established
○◐●●◐
Web UI for agent sessionsOpen — watching runtime/nx_agent_ui.nx : au_page, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. OpenHands app is the bar; our /project portal shows projects, not live agent sessions rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching au_page
Pros none measured yetCons behind OpenHands (leads), AutoGen; open contract; expected source declaration not established
○○◉○◐
Cost and token budget managementOpen — watching runtime/nx_agent_budget.nx : ab_meter, re-measured on every compare beat. Ship that symbol and this mark flips itself; the comparewatch- plane row flips with it. Every field agent meters provider spend; ours has nothing to meter (see the zero-token exceed) -- absent as a feature, moot by construction rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching ab_meter
Pros none measured yetCons behind SWE-agent, OpenHands, Aider, AutoGen; open contract; expected source declaration not established
○◐◐◐◐
Zero-LLM-token sovereign autonomous loopSource present; authored stronger claim: run_tool in runtime/nx_exec_engine.nx, verified at emit. The whole execute-verify-advance loop is compiled sovereign organs: 0 tokens, 0 API spend, deterministic, offline; every field agent burns provider tokens per action Adoption: BUILT-UNPROMOTED — PARTIAL: compiled, never promoted to the serving root: /api/promote it.
not adopted: compiled, never promoted to the serving root: /api/promote it
Pros Source symbol found; stronger capability claim is authored; ahead of SWE-agent, OpenHands, Aider, AutoGenCons not adopted yet: compiled, never promoted to the serving root: /api/promote it
◉○○○○
Refusal-over-fabrication by constructionSource present; authored stronger claim: run_tool in runtime/nx_exec_engine.nx, verified at emit. Gate-proven neg-control: a non-zero exit NEVER advances -- novel work is refused (NEEDS_TUTOR), not faked; the field's agents are notorious for claiming unverified success Adoption: BUILT-UNPROMOTED — PARTIAL: compiled, never promoted to the serving root: /api/promote it.
not adopted: compiled, never promoted to the serving root: /api/promote it
Pros Source symbol found; stronger capability claim is authored; ahead of SWE-agent, OpenHands, Aider, AutoGenCons not adopted yet: compiled, never promoted to the serving root: /api/promote it
◉○○○○
Machine-executable targets on stalled workstreamsDARK — runtime/nx_exec_engine.nx EXISTS but does not declare ee_target_declare: something shipped at this path under another name, and this mark would read open forever. Repoint the contract to the real entry point (the plan rung AND this row) or rename the function; the flip follows on the next beat, and the comparewatch- plane row reads DARK until then. The headline coverage number the engine prints itself: 0 of 104 stalled workstreams declare a target; a declared target is a row the engine can run rival marks uncited — the Yes, Best or Part codes on this row are an observation read with no reference mark behind them
dossierwatching ee_target_declare
Pros none measured yetCons behind SWE-agent, OpenHands (leads), Aider, AutoGen; open contract; expected source declaration not established
○●◉●●
Rival-claim provenance. Every Yes, Best or Part mark in a rival column is a claim about someone else's product. A cited row carries a reference mark that resolves to a pinned mirror (the refs gate measures that); an uncited row is an observation read and is badged in its evidence until a reference lands. The badge is the receipt, never the proof: a mark proves a mirror exists, not that the mirror supports the code. The rows are counted below.
Rival claims, counted
ClassCountNote
rows with rival marks15rows carrying a Yes, Best or Part in a rival column
cited7a reference mark resolves to a pinned mirror
uncited8an observation read, badged until a reference lands
rows, summed15RECONCILED: the parts sum to the total 15

Delivery and evidence

Inspect risks, technical debt, rendered observations, experiments and references. Read scope and limitations alongside every result.

Release history and work log

The worked plan, on the board. Every leg appends what it measured, landed, retracted, learned and left queued, per rung, so a crash leaves the next seat a ledger here rather than a transcript to mine. Kinds: measure, land, retract, lesson, queue. Newest last.
WhenRungKindEntry
2026-09-07R0queueOPERATOR SCOPE 2026-09-07: domain-to-evaluation-to-roadmap-to-experiments-to-reproducible-evidence autonomy is requested. Responsibility assignments are PROPOSED, not mechanically enforced: PM delivery accountability, engineer implementation, independent referee verification, operator authority and applicable legal/domain consultation. Meaning-making remains LLM-assisted interpretation with independent verification. This is requested work, not completed autonomy.
On these two registers. Rows are declared in the domain's plan file and carry the debt id, which is the join key back to the sovereign debt plane — that plane, not this page, is the authority on state. Reconciling them automatically (the regen reading the plane and refreshing these rows) is a named, owed rung; until it lands, treat an id here as a pointer to look up, not a status to trust.
Honest verdict. The Nishi team is a REAL governance-and-verification shell around autonomous work -- a zero-token machine execution loop that VERIFIES before advancing and REFUSES to fake novel work (gate-proven neg-control), an anti-drift coach that liar-kills SOTA claims against live censuses, heartbeat-liveness boards, governed conductor pulses, lineage tracking, and an honest autonomy meter. What it is NOT yet is a builder: the 2026-07-05 diagnosis stands unchanged -- zero of the 104 stalled workstreams declare a machine-executable target, the synthesizer covers toy arithmetic, and every novel organ still falls to Claude, while SWE-agent, OpenHands, and Aider ship LLM code-authorship as their entire product. The honest climb: give real workstreams machine-readable targets with heartbeat-on-advance, grow the synthesizer past toys, then wire an LLM-authoring lane UNDER the coach and verify gates the shell already provides -- the governance the field lacks wrapped around the authorship we lack.

Person · product · place — not yet measured for this domain

Every compare carries this layer. Declare knowledge/compare/team.ppp (rows surface|nishi or c1..c4|label|url|connect naming OUR live surface and each rival's front door), run nx_ppp_probe domain team, and this section fills itself on the next beat: the same ruler on both sides — privacy and CX (third-party hosts, tracker classes, cookies, security headers), design and longevity (design hygiene, computed WCAG contrast, render-blocking resources, unsized media, script weight, theme and motion queries), findability (landmarks, skip link, on-site search, breadcrumb, headings, internal links).

The field — discovered, not chosen

Rows written by nx_field_discover from team.seeds: the industry's own lists (Wikipedia wikitext, GitHub topics, awesome lists) read mechanically, every candidate counted across seeds. The matrix columns above are a SEAT'S pick; this band is the population they were picked from, and the stats line measures one against the other. A rival here is a lead, never a verdict — it earns a column when its capabilities are read and pinned.

Discovery receipt. One row per counter the run wrote, in the receipt's own order; the rival rows follow in their own table.
Field discovery, counted
ClassCountNote
seeds4
scanned4
fetched4
reused0
failed0
named4
candidates4
mentions4
capped0
RankRivalSeedsMentionsFirst seedKindLink
1SWE-agent11col0-swenamedhttps://github.com/SWE-agent/SWE-agent
2OpenHands11col1-openhandsnamedhttps://github.com/All-Hands-AI/OpenHands
3Aider11col2-aidernamedhttps://aider.chat/
4AutoGen11col3-autogennamedhttps://github.com/microsoft/autogen

field candidates 4|shown 4 of 4|matrix columns in the field 4 of 4|discovered rivals with no column 0|malformed rows 0 (counted, never rendered)|read-capped 0

Exclusive and shared capabilities

One capability is graded on one board; every other board references it. The fleet duplicate census (nx_rivalcensus dupes, on the fleetdupes clock row) reads every board's matrix and names each capability graded as a row on two or more boards, with a home derived from evidence: rung when exactly one board's plan contracts the symbol (that board is starred), gates when no plan contracts it and exactly one board's executed gate map runs the organ's gate (that board is plussed), ambiguous when several boards carry the deciding evidence (a decision for their seats), and none when no evidence decides it, with the reason beside it: unmapped (no board of the duplicate declares a gates map; declare the maps) or unproven (a map exists and runs none of the organ's gates; gate the organ on its proving board, or declare it a shared library by policy). A home elsewhere means this board should carry an @xrow reference to the home board's row rather than a graded row of its own; a home here means the other boards should. The table is this board's slice of one estate-wide census: the shape is shared, the rows are the board's.

This board grades 18 capabilities: 13 exclusive to it and 5 shared with other boards. Shared rows on this page: 5 = home here 0 + home elsewhere 0 + ambiguous 1 + undecided 4 + refused 0 (partition 5); undecided = unmapped 0 + unproven 4 + unevidenced 0; homonyms 0; since the previous census: new 0, resolved 0. Census FRESH age_s=6540.

CapabilityOrganBoards grading itHomeRuleEvidenceStanding on this board
gen_registernx_genealogist.nxgenealogy, team—noneunprovenundecided
cr_seednx_conductor_registry.nxjanitor, team—noneunprovenundecided
wc_countnx_ws_coach.nxreferee, team—noneunprovenundecided
fe_author_organnx_forge_engine.nxteam*, engineshift*—ambiguousplanambiguous
lb_onenx_forge_local_bench.nxteam, dataeng—noneunprovenundecided

Gaps from the record — what the estate does that no board carries

The record census (nx_goalmap record) reads the invoked-tool population and every plan queue row and files each organ or directive that NO matrix, plan or gates row names. A row here is a callout the boards missed: adjudicate it onto a board or declare it infrastructure. Census state STALE (age 1395645 s), sources read 4 of 7 declared — a BLIND census is a FLOOR: unread sources can only add rows.

kindnameboardsourceevidence

rows shown 0|this board's directives 0|estate-wide un-boarded organs 452 (listed in full on /compare/ecosystem)|census rows 639|malformed 0 (counted, never rendered)

References

Beyond a link list. Every reference below resolves twice — the publisher's copy and, where banked, the estate's own non-rottable library mirror with a content pin — and carries its evidence class plus the exact claim on this page it grounds. Keyed marks like [key] in the matrix notes jump here. A dash means honestly absent, never assumed.
  1. [sweagent2024] Yang, Jimenez, Wettig, Lieret, Yao, Narasimhan, Press. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. NeurIPS 2024. arXiv:2405.15793. publisher · read in our library knowledge/fetched/cmp_team_sweagent2024.html · pin h1589f706b0380d637196a65970b23cb89037465fe6d883af1007e34a41d8bdbf · accessed 2026-08-18 · published-paperGrounds: The SWE-agent column: Best on 'Issue-to-patch repository pipeline' (born from SWE-bench issue resolution, per the note) and Yes on 'LLM-driven code authoring (novel organ building)' -- the agent-computer-interface design that makes LLM code authorship the product.
  2. [sweagent-repo] SWE-agent/SWE-agent (GitHub repository; the v1.1.0 bar of 2025-05-22 was banked from its releases feed). Accessed 2026-08-18. publisher · read in our library knowledge/fetched/cmp_team_sweagent-repo.html · pin h9d88d10d6325dbd4e1be5b89224922f08f8d867490d0d8bdbc02f7a39968522f · accessed 2026-08-18 · vendor-docGrounds: The SWE-agent version bar in the matrix header (v1.1.0, 2025-05-22) and its Part code on 'Sandboxed per-task agent runtime'.
  3. [openhands2024] Wang, Li, Jiang, Xie, Chen et al. OpenHands: An Open Platform for AI Software Developers as Generalist Agents. arXiv:2407.16741, 2024 (ICLR 2025). publisher · read in our library knowledge/fetched/cmp_team_openhands2024.html · pin h2b9f10c47d1964713d513d8652d75cc988bbd3d7415f89abd8446bfab6e4e3c5 · accessed 2026-08-18 · published-paperGrounds: The OpenHands column: Best on 'Autonomous execute-and-verify loop on machine targets', 'LLM-driven code authoring', 'Sandboxed per-task agent runtime' (the docker runtime the note calls the bar) and 'Web UI for agent sessions'.
  4. [openhands-repo] All-Hands-AI/OpenHands (GitHub repository; the cloud-1.45.1 bar released 2026-07-09 was banked from its releases feed). Accessed 2026-08-18. publisher · read in our library knowledge/fetched/cmp_team_openhands-repo.html · pin hfb28c25cdbdd3cef48f4c4c0562cbd2098e206160fc9ef066e5cf3b6e8e5e2ba · accessed 2026-08-18 · vendor-docGrounds: The OpenHands version bar in the matrix header (cloud-1.45.1, 2026-07-09) and its Part codes on 'Work board with heartbeat liveness' and 'Teacher and practice loop'.
  5. [aider] Aider -- AI pair programming in your terminal (aider.chat docs; the v0.86.0 bar of 2025-08-09 was banked from its releases feed): repo map, diff edits, automatic git commits. Accessed 2026-08-18. publisher · read in our library knowledge/fetched/cmp_team_aider.html · pin h5c4361d45bfdf3a54ec8f3f17c8c8bf7da1aa975e34db2e36d02b6f5ab977770 · accessed 2026-08-18 · vendor-docGrounds: The Aider column: Best on 'Git-native pair-programming edit loop' -- the note names repo-map plus diff edits plus auto-commit as the bar, and this is the page that documents them.
  6. [autogen2023] Wu, Bansal, Zhang, Wu, Li et al. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155, 2023. publisher · read in our library knowledge/fetched/cmp_team_autogen2023.html · pin h67472921c0c51d0c9e39f3c51a32ab6cc617d181bfe478dccccd9b02ea5775db · accessed 2026-08-18 · published-paperGrounds: The AutoGen column: Best on 'Multi-agent conversation framework' and 'Governed scheduler (warden-owned conductor pulses)' as the orchestration-framework bar the notes name; our conductor schedules pulses and does not orchestrate agent dialogue.
  7. [autogen-repo] microsoft/autogen (GitHub repository; the python-v0.7.5 bar of 2025-09-30 was banked from its releases feed). Accessed 2026-08-18. publisher · read in our library knowledge/fetched/cmp_team_autogen-repo.html · pin h4607e57b4c2b7afba6f96e6b3dadd087f34191a0da106b875422c2df5e78d2ea · accessed 2026-08-18 · vendor-docGrounds: The AutoGen version bar in the matrix header (python-v0.7.5, 2025-09-30) and its Part codes on 'Sandboxed per-task agent runtime' and 'Human-in-the-loop approval flows'.
  8. [swebench2023] Jimenez, Yang, Wettig, Yao, Pei, Press, Narasimhan. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? ICLR 2024. arXiv:2310.06770. publisher · read in our library knowledge/fetched/cmp_team_swebench2023.html · pin hcd170cab3a56f891ee94070d5748d923685f2a84a91201d6336a221436fd0f9f · accessed 2026-08-18 · published-paperGrounds: The 'Benchmark-scored coding evaluation' row: SWE-bench pass rate is the field bar the note names, against which nx_forge_local_bench's byte-exact compile-and-run grader is present-not-best (measured 0/3 honest floor).

generated by nx_swcompare_matrix (sovereign NishiLang organ) from knowledge/compare/team.matrix · source checks show implementation presence; runtime and user-outcome evidence are reported separately · JavaScript supports page controls