Back to directory

Agenta

An open-source workspace where a team builds and runs AI agents and automations by chatting with them, connecting them to existing apps, and scheduling them to run in the background.

Agenta

Agenta is an open-source workspace for building agents that automate or augment work. Agents are built conversationally: you describe the task, connect the applications the agent needs, and refine it through feedback, then use it directly in chat or share it with a team.

Self-hosted, it can run with an existing Claude or ChatGPT subscription instead of metered API billing, and supports Claude Code, Pi and Codex as harnesses, with agents defined through AGENTS.md files, skills and MCP servers. Background agents run on a schedule or in response to an event, and the platform traces every run, keeps a version history of each agent's configuration, and lets teams set which tool actions run automatically, need approval, or are blocked.

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.