Back to directory

FastClaw

A lightweight, single-binary AI agent runtime written in Go that creates, manages, and runs multiple agents, each with its own personality, memory, skills, and sandboxed tool execution, through a web dashboard.

FastClaw

FastClaw is an Agent Factory: a runtime, written in Go, that creates, manages, and runs AI agents, each with its own personality file, memory, skills, and tools, while FastClaw itself handles LLM communication, tool execution, sandbox isolation, and session management. It installs as a single binary through a shell script on macOS and Linux or a PowerShell script on Windows.

A first run opens a setup wizard that configures an LLM provider and creates a default agent, after which a web dashboard on a local port manages agents, skills installed from ClawHub or GitHub, LLM provider configuration (OpenAI, Anthropic, Ollama, OpenRouter, and others), programmatic API keys at admin, user, and agent tiers, and settings. Non-admin users get scoped access to models, API keys, and general and account settings, seeing admin-shared resources as inherited entries they can layer private overlays on top of.

Each agent's own management panel edits its personality and memory files, installs agent-private skills, overrides its model, and connects it to IM channels such as Telegram, Discord, and Slack.

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.