Back to directory

Open Claude Tag

A free, self-hostable, LLM-agnostic alternative to Anthropic's Claude Tag, giving a Slack channel one shared AI teammate instead of a personal per-user assistant.

Open Claude Tag

Open Claude Tag gives a Slack channel one shared agent with persistent memory, rather than the isolated, per-user DM assistants common in most Slack AI bots. Everyone in the channel sees the same context, can pick up mid-thread, and the agent knows who said what.

It works with Claude, GPT-4o, Gemini, Groq or a local Ollama model, selectable per channel through an environment variable, and is self-hostable without a paywall or cloud lock-in to a single vendor. After each conversation the agent decides what is worth keeping and writes it to a MEMORY.md file rather than logging everything, and it can auto-create new skills after complex multi-step tasks so it improves over time.

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.