Back to directory

IntentKit

An open-source, self-hosted cloud agent cluster that runs a collaborative team of AI agents able to call each other and connect to social platforms and Web3.

IntentKit

IntentKit runs agents in the cloud rather than on local hardware, aiming for minimal local resource use, zero maintenance, and higher reliability than a personal-assistant-style local agent. Agents in a cluster can call and interact with each other, are designed so they cannot access a user's secret keys directly, and can connect to social platforms and optional Web3 and blockchain integrations.

It can be run as a self-deployed cluster, imported and extended as a Python library to add agent-cluster capabilities to an existing project, or driven from an external application through its built-in API endpoints. The project currently does not accept code contributions through pull requests, but does take feature requests and bug reports through GitHub Issues.

It is written in Python and distributed under the MIT license.

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.