BichengWang / multi-agents
Multi-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.
Why this job: says: agent teams, multi agent; topics: multi-agent, multi-agent-systems, agent-orchestration, ai-agents
What it does
Verified, 7.2 points *better* than mini-SWE-agent but only 0.4 above the strongest single-agent baseline, with different models per role (Agyn). A decentralized pair, a patch editor and a validator with isolated context, gained 3.6 and 8.4 points over mini-SWE-agent (icat-agent).
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 158
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.0
- Released 21 days ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 95 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| y5ez3g / facadecode | 252 | yesterday | MIT | Mac, Linux |
| flyhero / antumi | 109 | yesterday | Apache-2.0 | Mac, Windows, Linux |
| avirtual / clodex | 135 | today | Apache-2.0 | Mac |
More: languages, topics and project record
Languages
- Python 100%
- Makefile <1%
- Shell <1%
Topics
- agent-orchestration
- ai-agents
- benchmark
- claude-code
- codex
- coding-agents
- git-worktree
- llm
- multi-agent
- multi-agent-systems
- openai-agents-sdk
- swe-bench
Project record
- JobAgent frameworks
- StatusListed
- Commits128
- Forks12
- Watching16
- Stars in 28 days+83
- CreatedApr 21, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026