humanlayer vs SWE-agent
The two are close in size: 11.7k stars for humanlayer, 20.6k for SWE-agent. Over the days we have tracked them humanlayer moved +5.1% and SWE-agent +3.6%, so humanlayer is growing faster right now.
SWE-agent leads on context depth and noise control and customization and privacy and model freedom and setup ease. humanlayer does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
This repository is an archived/deprecated reference implementation and public issue history that points to an actively rebuilt service at humanlayer.com.
- Stars
- 11.7k
- Tracked growth
- +5.1%
- Maturity
- ●●●●●
- Last commit
- 4d ago
- Language
- TypeScript
- License
- NOASSERTION
- Cost to run
- Unclear; depends on deployment
State-of-the-art open-source agent focused on autonomously fixing GitHub issues and offering a specialized EnIGMA mode for offensive cybersecurity, all governed by a single YAML.
- Stars
- 20.6k
- Tracked growth
- +3.6%
- Maturity
- ●●●●●
- Last commit
- 12h ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key (cloud LMs)
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | humanlayer | SWE-agent |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff only | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● No controls | ●●●●● Basic config filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● No customization | ●●●●● YAML config |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Third-party cloud | ●●●●● Your API key |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Fixed provider | ●●●●● Any BYO model |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Complex setup | ●●●●● One-click demo |
Which one to pick
Pick humanlayer if…
Archived/reference — inspect historical implementation and issue history or follow the maintained rebuild at humanlayer.com rather than use this deprecated code directly.
Pick SWE-agent if…
SOTA performance — pick SWE-agent when you want a research-grade, configurable autonomous agent (with an easy Codespaces demo) that can fix repo issues and run security experiments.
- Context depth: Diff + related files (3/5 against 1/5)
- Noise control: Basic config filters (3/5 against 1/5)
- Customization: YAML config (3/5 against 1/5)
- Privacy: Your API key (3/5 against 1/5)
- Model freedom: Any BYO model (5/5 against 1/5)
- Setup ease: One-click demo (5/5 against 1/5)
What people want from each one
humanlayer/humanlayer
Hacker News: Show HN: HumanLayer – Human-in-the-Loop for AI Agents drew 5 points and 2 comments.
SWE-agent/SWE-agent
Hacker News: Princeton group open sources "SWE-agent", with 12% fix rate for GitHub issues drew 307 points and 143 comments.
Questions people ask
Is humanlayer better than SWE-agent?
SWE-agent leads on context depth and noise control and customization and privacy and model freedom and setup ease. humanlayer does not take any axis by a clear margin. humanlayer is worth picking when archived/reference — inspect historical implementation and issue history or follow the maintained rebuild at humanlayer.com rather than use this deprecated code directly.
Which of humanlayer and SWE-agent keeps my code private?
humanlayer: Third-party cloud (1/5). SWE-agent: Your API key (3/5).
What does each one cost to run?
humanlayer: Unclear; depends on deployment. SWE-agent: Your API key (cloud LMs).
Full profiles: humanlayer/humanlayer and SWE-agent/SWE-agent. Everything else in Autonomous SWE agents.