OpenCollab
A research-friendly, high-performance multi-agent collaboration coding framework.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 17 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/RISE-X-Lab/OpenCollab with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/RISE-X-Lab/OpenCollab'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/rise-x-lab--opencollab)HTML
<a href="/listings/rise-x-lab--opencollab"><img src="/api/listings/rise-x-lab--opencollab/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
uv sync --locked cp configs/.env.example configs/.env # then set OPENCOLLAB_API_KEY uv run opencollab --workspace .
`configs/.env` accepts any OpenAI-compatible or Anthropic endpoint. Never commit real API keys. The command starts the built-in Self-Collaboration team: the Analyst delegates to independent Coder and Tester workspaces and adopts the Coder's changes before testing. See [cooperative teams](opencollab/README.md#cooperative-teams) for adoption, conflicts, and recovery. Custom teams choose their own tools. Type `/help` in the terminal for navigation, saving and exit controls. To define additional roles, create and select an explicit team file as shown below. To run Duo on a Git repository, use this command.
uv run opencollab workflow run duo --workspace /path/to/repository \
--task 'Fix the public issue described here.' \
--args '{"allow_unisolated_shell":true}'Place run options such as `--workspace`, `--model` and `--budget` after `workflow run NAME`. To list workflows in another workspace, use `workflow list --workspace PATH`. Options placed before the `workflow` subcommand are interpreted as belonging to the root interactive mode and will produce a usage error.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 197 lines
- <p align="center">
- <a href="assets/readme-hero-light.svg#gh-light-mode-only"><img src="assets/readme-hero-light.svg#gh-light-mode-only" alt="OpenCollab. Program how coding agents collaborate. Verify that they did." width="880"></a>
- <a href="assets/readme-hero-dark.svg#gh-dark-mode-only"><img src="assets/readme-hero-dark.svg#gh-dark-mode-only" alt="OpenCollab. Program how coding agents collaborate. Verify that they did." width="880"></a>
- </p>
- <p align="center">
- A multi-agent coding framework with programmable collaboration and a controllable runtime.
- </p>
- <p align="center">
- <a href="https://arxiv.org/abs/2609.38345"><img src="https://img.shields.io/badge/arXiv-2609.38345-B31B1B.svg?style=flat-square&labelColor=0F172A" alt="arXiv 2609.38345"></a>
- <a href="https://rise-x-lab.github.io/OpenCollab/"><img src="https://img.shields.io/badge/Project-Page-7C3AED.svg?style=flat-square&labelColor=0F172A" alt="Project page"></a>
- <a href="https://github.com/RISE-X-Lab/OpenCollab/releases/latest"><img src="https://img.shields.io/github/v/release/RISE-X-Lab/OpenCollab?style=flat-square&color=7C3AED&labelColor=0F172A" alt="Latest release"></a>
- <a href="https://github.com/RISE-X-Lab/OpenCollab/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MulanPSL--2.0-blue.svg?style=flat-square&color=5556EC&labelColor=0F172A" alt="License: MulanPSL-2.0"></a>
- <img src="https://img.shields.io/badge/python-3.10--3.14-blue.svg?style=flat-square&color=2563EB&labelColor=0F172A" alt="Python 3.10 through 3.14">
- <a href="https://github.com/RISE-X-Lab/OpenCollab/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/RISE-X-Lab/OpenCollab/ci.yml?branch=main&style=flat-square&label=CI&labelColor=0F172A" alt="CI"></a>
- <br>
- <sub><b>English</b> · <a href="README.zh-CN.md">Chinese</a></sub>
- </p>
- OpenCollab follows a **rigorous and restrained software engineering philosophy**. In [version 0.9.3](https://github.com/RISE-X-Lab/OpenCollab/releases/tag/v0.9.3), its harness core in the [OpenCollab/opencollab directory](https://github.com/RISE-X-Lab/OpenCollab/tree/v0.9.3/opencollab), written in **under 50,000 lines**, provides comprehensive research instrumentation and statistics while **outperforming Claude Code, Codex CLI and OpenHands** across several [coding benchmarks](https://github.com/RISE-X-Lab/OpenCollab/blob/main/docs/results.md). The core implementations of these mature competitors have codebases spanning **well over 100,000 lines**. OpenCollab also **won first place** at the [OAIC Agentic Software Factory Hackathon](https://create.gosim.org/factory26/), which featured a **$24,000 prize pool**.
- <p align="center">
- <a href="assets/benchmark-hero-light.svg#gh-light-mode-only"><img src="assets/benchmark-hero-light.svg#gh-light-mode-only" alt="Pass@1 of six harnesses using GPT-5.6-Luna at max reasoning effort. OpenCollab (Duo) scores 68.91% on SWE-bench Pro, 83.15% on Terminal-Bench 2.1, and 65.49% on DeepSWE." width="980"></a>
- <a href="assets/benchmark-hero-dark.svg#gh-dark-mode-only"><img src="assets/benchmark-hero-dark.svg#gh-dark-mode-only" alt="Pass@1 of six harnesses using GPT-5.6-Luna at max reasoning effort. OpenCollab (Duo) scores 68.91% on SWE-bench Pro, 83.15% on Terminal-Bench 2.1, and 65.49% on DeepSWE." width="980"></a>
- </p>
- <p align="center">
- <sub><a href="docs/results.md">Full results</a></sub>
- </p>
- ## News
- - ⭐ **2026-11-07** — OpenCollab reached **1,000 stars on GitHub**.
- - 🏆 **2026-10-11** — **[Won first place](https://create.gosim.org/factory26/)** at the OAIC Agentic Software Factory Hackathon using OpenCollab! 🏆
- - 🎉 **2026-10-08** — [OpenCollab 0.9.3 (v1.0.0 PreRelease)](https://github.com/RISE-X-Lab/OpenCollab/releases/tag/v0.9.3)
- includes the latest Duo V8 workflow and all the statistical features described
- in our paper to support research experiments. Following extensive testing and
- bug fixes, the framework now offers the complete feature set planned for 1.0.0.
- We will release version 1.0.0 once our paper is accepted. See the
- [changelog](CHANGELOG.md#093---2026-10-08).
- - **2026-09-29** — Our paper is on arXiv: [*OpenCollab: A Multi-Agent Coding Framework with
- Programmable Collaboration and Controllable Runtime*](https://arxiv.org/abs/2609.38345).
- - **2026-09-27** — [OpenCollab 0.8](https://github.com/RISE-X-Lab/OpenCollab/releases/tag/v0.8.0)
- ships [Duo](docs/duo.md) built in and makes [Single2](docs/single2.md) the
- default Base agent.
- - 🎉 OpenCollab has been selected for support by the **Seed Program of the
- Youth Open Source Special Fund**.
- ## Quick start
- ```bash
- uv sync --locked
- cp configs/.env.example configs/.env # then set OPENCOLLAB_API_KEY
- uv run opencollab --workspace .
- ```
- `configs/.env` accepts any OpenAI-compatible or Anthropic endpoint. Never commit
- real API keys. The command starts the built-in Self-Collaboration team: the
- Analyst delegates to independent Coder and Tester workspaces and adopts the
- Coder's changes before testing. See [cooperative teams](opencollab/README.md#cooperative-teams)
- for adoption, conflicts, and recovery. Custom teams choose their own tools.
- Type `/help` in the terminal for navigation, saving and exit controls.
- To define additional roles, create and select an explicit team file as shown below.
- To run Duo on a Git repository, use this command.
- ```bash
- uv run opencollab workflow run duo --workspace /path/to/repository \
- --task 'Fix the public issue described here.' \
- --args '{"allow_unisolated_shell":true}'
- ```
- Place run options such as `--workspace`, `--model` and `--budget` after
- `workflow run NAME`. To list workflows in another workspace, use
- `workflow list --workspace PATH`. Options placed before the `workflow`
- subcommand are interpreted as belonging to the root interactive mode and
- will produce a usage error.
- ## Program the collaboration
- <p align="center">
- <a href="assets/oc-hero-light.svg#gh-light-mode-only"><img src="assets/oc-hero-light.svg#gh-light-mode-only" alt="OpenCollab Team and Workflow modes" width="1200"></a>
- <a href="assets/oc-hero-dark.svg#gh-dark-mode-only"><img src="assets/oc-hero-dark.svg#gh-dark-mode-only" alt="OpenCollab Team and Workflow modes" width="1200"></a>
- </p>
- - **Team.** A YAML file declares each role's prompt, model, tools, and token
- allowance, the context policy, and who may message whom. Start from the
- built-in team and edit it:
- ```bash
- uv run opencollab team init team.yaml # edit roles, prompts, tools, and topology
- uv run opencollab team show --team-config team.yaml
- uv run opencollab --team-config team.yaml --workspace .
- ```
- - **Workflow.** A Python module issues every handoff. Duo is one;
- [write your own](opencollab/README.md#workflow-authoring) and run it with
- `opencollab workflow run NAME`.
- ## Examples
- **[First place at the OAIC Hackathon](examples/arcbench-evolution-r6/).**
- OpenCollab powered the **first-place solution** at the
- [OAIC Agentic Software Factory Hackathon](https://create.gosim.org/factory26/),
- which offered a **$24,000 prize pool**. Explore the winning approach in the
- ARC-Bench r6 example and build on it for your own applications.
- **[From 24,000 lines to a 239-line example](examples/mini-edict/).**
- [Edict](https://github.com/cft0808/edict) is a multi-agent project of roughly
- **24,000 lines**. Mini Edict's original implementation recreates its core
- collaboration protocol in **239 lines** of team and workflow code, showing how
- OpenCollab makes sophisticated multi-agent designs compact and easy to extend.
- **[98.3% on a NeurIPS 2026 benchmark](examples/io2code_oc/).** IO2CodeBench was
- introduced in [FromIO](https://arxiv.org/abs/2605.15334), accepted at NeurIPS 2026.
- Built on OpenCollab, this example reports a resolve rate of **98.3% (113/115)**,
- up from its **78.3% (90/115)** fixed-example baseline with the same `gpt-6-luna`
- model, a **20-percentage-point gain** across the benchmark's 115 non-multimodal
- tasks.
- [See the results](examples/io2code_oc/#results).
- ## Verify it happened
- In a Team, the agents decide the handoffs, and a declared team does not
- guarantee that they happen. In our runs, the lead agent often briefed its
- teammates and then did the work itself. OpenCollab enforces the declaration and
- records what each agent did:
- - a message along an undeclared edge is refused, and the refusal is recorded;
- - each agent's token budget is checked before every model call;
- - `--trace` writes one JSONL record per step, stamped with the run, agent, role,
- event type, and token usage.
- From these records we measure **Adherence**, the share of runs in which the
- declared organization actually happened. Changing one setting of the same team
- raised it from 47.2% to as much as 97.2%.
- See [how Adherence is measured](docs/adherence.md).
- ## Learn more
- | Guide | What it covers |
- | --- | --- |
- | [Package guide](opencollab/README.md) | CLI, Python API, architecture, and runtime behavior |
- | [Configuration guide](configs/README.md) | Providers, models, and team files |
- | [Duo guide](docs/duo.md) | Running the dual-coder workflow from the CLI and SDK |
- | [Weave guide](docs/weave.md) | Ordered sessions, executable checks, bounded repair and continuation |
- | [Benchmark results](docs/results.md) | Tokens, cost, the paired Duo–Base test, and how to run an evaluation |
- | [Adherence](docs/adherence.md) | What the runtime records, and how we measure Adherence |
- | [OpenCollab-Eval README](https://github.com/RISE-X-Lab/OpenCollab-Eval#readme) | Running agents on software-engineering benchmarks |
- | [Documentation index](docs/README.md) | Skills, migration guides, and design records |
- | [CONTRIBUTING.md](CONTRIBUTING.md) | Development checks, [testing](CONTRIBUTING.md#checks-must-pass-before-a-pr), and [releases](RELEASING.md) |
- ## Citation
- If you find OpenCollab useful, please give it a ⭐ and cite our work. Our paper is
- [*OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and
- Controllable Runtime*](https://arxiv.org/abs/2609.38345). OpenCollab builds on
- [Self-Collaboration](https://arxiv.org/abs/2304.07590):
- ```bibtex
- @misc{hsu2026opencollab,
- author = {Hsu, Chun-Wah and Gong, Kai and Wu, Yu and Chen, Xianhe and
- Liu, Mengyang and Li, Jie and Li, Hanyu and Liu, Zhixuan and
- Tang, Naisheng and Chi, Jiaying and Fan, Ziheng and He, Xuning and
- Yang, Xiaokang and Jiang, Xue and Dong, Yihong},
- title = {OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime},
- year = {2026},
- eprint = {2609.38345},
- archivePrefix = {arXiv},
- url = {https://arxiv.org/abs/2609.38345}
- }
- @article{dong2023self,
- author = {Dong, Yihong and Jiang, Xue and Jin, Zhi and Li, Ge},
- title = {Self-Collaboration Code Generation via ChatGPT},
- journal = {ACM Transactions on Software Engineering and Methodology},
- volume = {33},
- number = {7},
- pages = {189:1--189:38},
- year = {2024}
- }
- ```
- ## License
- OpenCollab is licensed under the [Mulan Permissive Software License v2](https://github.com/RISE-X-Lab/OpenCollab/blob/main/LICENSE)
- (`MulanPSL-2.0`).
- ## Star History
- <p align="center">
- <a href="https://www.star-history.com/?repos=RISE-X-Lab%2FOpenCollab&type=date#gh-light-mode-only">
- <img src="https://api.star-history.com/svg?repos=RISE-X-Lab/OpenCollab&type=Date#gh-light-mode-only" alt="OpenCollab star history chart" width="600">
- </a>
- <a href="https://www.star-history.com/?repos=RISE-X-Lab%2FOpenCollab&type=date#gh-dark-mode-only">
- <img src="https://api.star-history.com/svg?repos=RISE-X-Lab/OpenCollab&type=Date&theme=dark#gh-dark-mode-only" alt="OpenCollab star history chart" width="600">
- </a>
- </p>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.