autoresearch agents

uditgoenka/autoresearch

Agent

Writes and updates project documentation from structured scout reports, explicit file targets, and project context.

evo-hq/evo

Agent

Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation, leakage, gates, plumbing); read-only. mode=review-experiment -- post-commit per-task failure analysis for a specific experiment; reads per-task traces and the eval-runner log, writes per-task…

evo-hq/evo

Agent

Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (failureanalysis, literature, or frontierextrapolation) and appends proposals as JSONL lines to a shared file the orchestrator reconciles. Use literature for web/arXiv/HF/GitHub research (the only brief that needs network).…

evo-hq/evo

Agent

Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set leakage in training data, subsetted eval commands, missing gates for new artifacts, generic hypotheses, cache short-circuits, fake artifacts, and score-reproducibility failures. Returns…

Human-Agent-Society/CORAL

Agent

Verify that every claim in a research note is grounded in its linked raw sources.

Human-Agent-Society/CORAL

Agent

Decide what to do with two notes flagged as near-duplicates — without knowing which is which.

Human-Agent-Society/CORAL

Agent

Use this subagent to turn "optimize / speed up / improve this with CORAL" into a working CORAL task. Give it the code (or just a repo and a rough goal) and it acts immediately — explores the repo to infer the optimization target, scaffolds a .coralworkspace/, writes the grader, and iterates coral validate until the…

vlasenkoalexey/tpu_performance_autoresearch_wiki

Agent Claude Code

Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…

vlasenkoalexey/tpu_performance_autoresearch_wiki

Agent Claude Code

Independent verifier for kernel-family experiments (the Roles section's verifier for the pallas lane). Given a final candidate kernel + the naive baseline, it independently re-benchmarks both in a fresh process, re-runs numerical parity, captures traces/LLO dumps with the canonical flag set, runs the hypothesis-firing…

vlasenkoalexey/tpu_performance_autoresearch_wiki

Agent Claude Code

Analyze a single completed experiment's xprof trace + HLO dump and return structured ## Profile + ## HLO Dump markdown sections that slot directly into the experiment page. Phases: Phase 1 walks xprof (bucket attribution, dominant ops, memory profile); Phase 2 walks HLO (module sizes, fusion verification, regression…

StepzeroLab/research-git

Agent

Regenerates a recalled Feature Capsule onto the CURRENT codebase. Given a regeneration brief (the capsule's intent/knobs/data-assumptions/resurrection guide + the live source of the regions it touches), it re-implements the feature into today's code — adapting to refactors — and leaves a reviewable diff. It never runs…

StepzeroLab/research-git

Agent

Segments a raw git diff into clean, high-quality Feature Capsules. Separates real features from infrastructure noise, and for each feature writes intent, knobs, assumptions, and an operational resurrection guide. This is the "Phase 2" semantic step that replaces the free heuristic segmenter — it runs on the host…

StepzeroLab/research-git

Agent

Judges graph edges between Feature Capsules. Two jobs: (1) confirm or reject candidate dependson edges that the deterministic engine over-produced from name overlap; (2) classify each baseline overlaps pair (capsules touching the same code region) into a more precise relationship. Runs on the host session's…

arbazkhan971/godmode

Agent

Executes implementation tasks following a Godmode skill workflow exactly.

arbazkhan971/godmode

Agent

Runs the autonomous optimization loop — measure, modify, verify, keep/revert.

arbazkhan971/godmode

Agent

Security auditor — STRIDE, OWASP Top 10, red-team analysis.

GodModeAI2025/skill-forge

Agent

Analysiere Eval-Failures / Metrik-Ergebnisse und generiere eine testbare Verbesserungshypothese.

GodModeAI2025/skill-forge

Agent

Wende eine Hypothese als gezielte Änderung auf die Zieldateien an.

GodModeAI2025/skill-forge

Agent

Koordiniert den Agent-Lifecycle im Skill Forge Loop.

proyecto26/autoresearch-ai-plugin

Agent

Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→measure→keep/discard experiments — and return a structured checkpoint. Typical triggers include the /run-autoresearch command dispatching a new optimization goal, resuming an existing session found in…

zircote-plugins/autoresearch

Agent

Agent "convergence-reporter" from zircote-plugins/autoresearch, covering convergence reporter agent, context, role, inputs and process.

zircote-plugins/autoresearch

Agent

This agent is spawned in two situations.

zircote-plugins/autoresearch

Agent

This agent is spawned during the autoresearch improvement loop when a candidate skill needs modification based on eval results. It runs once per iteration, reading grading failures and modifying the candidate skill to address them.