# fastclaw-ai/fastclaw

Multi-Agent Framework

Repository: https://github.com/fastclaw-ai/fastclaw
Canonical: https://ross.abutalabs.com/products/fastclaw
Homepage: https://fastclaw.ai
Language: Go
License: NOASSERTION
License Family: other
Topics: agent-factory, agent-runtime, fastclaw, multi-agent, openclaw-alternative
Last push: 2026-08-22T14:40:46+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 81, longevity 12
- inputs: {"age_days": 177, "days_push": 11, "days_rel": 44, "gap_med": 0, "n_releases_24m": 74}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1291, forks 216 (observed 2026-08-28T04:04:16.016798+00:00)

## What it is
FastClaw is a lightweight AI agent runtime written in Go, distributed as a single binary. It acts as an agent factory that creates, manages, and runs multiple AI agents, each with its own personality, memory, skills, tools, and messaging channels.

## Use cases
- run self-hosted AI agents with custom personalities
- connect LLM agents to Telegram, Discord, or Slack
- manage multiple agents from a web dashboard
- execute agent tools in a sandboxed environment
- expose an OpenAI-compatible chat completions API
- schedule cron jobs triggered by agents

## When to choose
- you want a single-binary, self-hosted agent runtime with no dependencies
- you need multi-agent management with per-agent models, skills, and memory
- you want to connect agents to IM platforms like Telegram, Discord, or Slack
- you prefer Go-based tooling and cloud/Docker sandbox isolation

## When to avoid
- you need a Python or TypeScript agent SDK to embed in your own code
- you require deep LangChain-style orchestration pipelines or graph workflows
- you need a fully permissively licensed library (license is source-available, not standard OSS)

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, mcp, scheduling, webhook, api-framework
- domain: large-language-models, chatbots, self-hosted
- platform: windows, self-hosted, go
- tags: agent-runtime, agent-factory, multi-agent, sandbox, openai-compatible-api, telegram-bot, discord-bot, slack-bot, single-binary, skills, ai-agents, automation, linux, macos, docker

## Member repositories
- fastclaw-ai/fastclaw (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:16.016798+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:54:47.032293+00:00, confidence not recorded.
  - readme: https://github.com/fastclaw-ai/fastclaw (fetched 2026-08-28T04:04:16.016798+00:00, sha ae6481099004)
  - homepage: https://fastclaw.ai (fetched 2026-08-29T12:11:13.293152+00:00, sha 18ababca85c6)
- Data as of 2026-08-30T08:39:29.467469+00:00.