ai scientist agents

Sibyl-Research-Team/AutoResearch-SibylSystem

Agent Claude Code

Sibyl Research System heavy-reasoning agent. Used for deep analysis tasks: synthesis, supervision, editing, critical review, and reflection.

Sibyl-Research-Team/AutoResearch-SibylSystem

Agent Claude Code

Sibyl Research System lightweight agent. Used for quick evaluation tasks: debate roles (optimist, skeptic, strategist), section critique, and cross-critique.

Sibyl-Research-Team/AutoResearch-SibylSystem

Agent Claude Code

Sibyl Research System standard agent. Used for literature research, planning, experiment design, and idea generation.

zjunlp/Mechanist

Agent

The claim agent of /auto. Runs the /auto-claim skill under two orthogonal axes — BEHAVIORSOURCE (given / given-validation / discovery) sets where the behavior comes from and whether it is validated; MECHANISM (given / discovery) sets who picks the mechanism method. discovery generates ranked, novelty-checked ideas…

zjunlp/Mechanist

Agent

The experiment agent of /auto. Wraps the /auto-experiment skill, which folds mechanism-family routing inline before implementing, code-reviewing, and deploying the experiment suite. Supports two-step invocation — first call returns candidate families for the orchestrator's mini-prompt, second call (with chosenfamily)…

zjunlp/Mechanist

Agent

The iteration agent of /auto. Runs the /auto-iteration-loop skill — an autonomous review loop that consumes /auto-verify's four-state output (PASS / FAIL / INCONCLUSIVE / ZEROELIGIBLEVARIANTS) plus the orthogonal deferred bucket and routes each claim to the right back-edge (① variant-only fix / ② baseline-script fix /…

AutoResearch-Factory/Agon

Agent

Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.

AutoResearch-Factory/Agon

Agent

Screen experiment plans before implementation, blocking unnecessary scale and meaningless gates.

AutoResearch-Factory/Agon

Agent

Research a topic landscape, generate and select research ideas, and save them under ideas/.

whenpoem/aiscientist

Agent Claude Code

Implementation and experimentation. Can write code, run scripts, and record findings to memory.

whenpoem/aiscientist

Agent Claude Code

Attempt formal proofs in Lean 4 for stated lemmas. Scope: small statistical identities (sample mean unbiasedness, Chebyshev/Cauchy-Schwarz/Markov/Bonferroni inequalities, simple CLT/MLE statements). Triage gate: only spawn when triageforformalization returns eligible=True.

whenpoem/aiscientist

Agent Claude Code

Adversarial reviewer of finished manuscripts. Refuses to sign off on central result claims until publication-critical metrics trace back to pinned evidence (empirical checklist) AND theorem claims trace back to an empty diagnostic manifest plus either a Lean verification or an explicit unverified flag (proof…

samsamurai301/Researcher-AI

Agent

Coordinate an auditable Researcher AI project from hypothesis through artifact review while enforcing execution and disclosure gates.