Back to directory

OctoMatrix

A self-hosted multi-agent framework that lets you command AI agents with different specialties for coding, data retrieval and analysis from Telegram, Discord or Slack, coordinated by a persistent grep-based memory system and a standardized agent harness.

OctoMatrix

OctoMatrix is a remote AI collaboration environment that integrates an AI engine with Telegram, Discord and Slack so an operator can command multiple specialized AI agents from a phone or computer. It runs multi-agent teams with workspace isolation and dynamically configured collaboration, natively on Linux and macOS, and on Windows through WSL.

Its Cyberbrain long-term memory system uses grep-based retrieval instead of vector search, compressing conversation highlights into indices and extracting historical context on demand so agents can retrospect beyond the context window. Cross-platform support lets a team switch between Telegram, Discord and Slack while keeping agent state and task progress in sync, and an agent harness framework constrains agents to a standardized, predictable workflow instead of unconstrained model output.

Built with Python. Apache-2.0 licensed.

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.