Back to directory

AxisAgentic

AxisAgentic is an extensible runtime for long-horizon AI agents that also records the trajectories those agents produce, so the same execution traces can support replay, benchmark evaluation and supervised fine-tuning data export.

AxisAgentic

AxisAgentic is an extensible runtime for long-horizon AI agents built around OpenAI-compatible endpoints and pluggable local model clients. It handles multi-turn execution, tool orchestration, context management, recovery and benchmark evaluation, and every task writes an append-only trace that preserves the state the model saw at each stage.

Because model clients, tools, orchestrators, datasets, evaluators, reward functions and recipe policies are all replaceable, the same runtime can back different agent recipes; its reference recipes are search agents. Traces can be replayed to reconstruct context, used for evaluation, or exported for supervised fine-tuning, with the source trace and task status preserved. It does not include model weights.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.