# chmod777john/swarm-ide

为 Agent Swarm 打造的 IDE ，支持 Kimi-2.5, GLM-4.7 等（即使不像 K2.5 那样经过强化学习的模型也能用）An IDE built for Agent Swarms, supporting Kimi-2.5, GLM-4.7, and more (compatible with models even without RL-reinforcement like K2.5).

Repository: https://github.com/chmod777john/swarm-ide
Canonical: https://ross.abutalabs.com/products/swarm-ide
Homepage: https://agents.flex42.dev
Language: TypeScript
License Family: other
Last push: 2026-03-02T02:43:53+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 17
- inputs: {"age_days": 244, "days_push": 184, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1500, forks 177 (observed 2026-08-28T04:04:54.242596+00:00)

## What it is
Swarm-IDE is a self-hosted IDE for orchestrating self-organizing agent swarms, where agents dynamically create sub-agents and communicate via minimal create/send primitives. It provides a WeChat-style chat interface, a live graph visualization of the swarm topology, and MCP tool support, working with models like Kimi-2.5 and GLM-4.7.

## Use cases
- orchestrate a swarm of AI agents that spawn sub-agents dynamically
- chat directly with any sub-agent in a multi-agent system
- visualize live agent collaboration topology as a graph
- run multi-agent workflows without predefined LangGraph-style DAGs
- connect MCP tools to a multi-agent coding environment
- debug agent context and tool calls in real time

## When to choose
- you want emergent, fluid agent topologies instead of static workflow graphs
- you need human-in-the-loop intervention at any level of an agent hierarchy
- you want an open-source alternative to Kimi-Swarm or Claude Agent Teams
- you prefer chat-based (IM-style) interaction with agents

## When to avoid
- you need a production-hardened, licensed tool - it has no license and is a proof of concept
- you require predefined, deterministic agent pipelines
- you cannot run Linux/Docker or use Bun
- you need guaranteed stability or long-term support

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, chat-interface, mcp, llm-inference, data-visualization
- domain: large-language-models, developer-tools, chatbots
- platform: bun, self-hosted
- tags: multi-agent, agent-swarm, ide, wechat-style-ui, dynamic-topology, sub-agents, human-in-the-loop, proof-of-concept, ai-agents, linux, web-server, docker, typescript

## Member repositories
- chmod777john/swarm-ide (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.242596+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 2026-08-30T04:32:59.488204+00:00, confidence not recorded.
  - readme: https://github.com/chmod777john/swarm-ide (fetched 2026-08-28T04:04:54.242596+00:00, sha 2b71eda32a48)
  - homepage: https://agents.flex42.dev (fetched 2026-08-29T11:38:17.047936+00:00, sha 0553a288f668)
- Data as of 2026-08-30T08:39:29.467469+00:00.