DeepCode vs SWE-agent
The two are close in size: 16.5k stars for DeepCode, 20.2k for SWE-agent. Over the days we have tracked them DeepCode moved +4.7% and SWE-agent +4.1%, so DeepCode is growing faster right now.
They split the axes: DeepCode leads on context depth and customization, SWE-agent on setup ease.
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
DeepCode pairs multi-agent delegation and reusable SKILL playbooks with autonomous, test-driven loops and parallel workers so it can decompose large features, run them in isolation, and iterate until tests pass.
- Stars
- 16.5k
- Tracked growth
- +4.7%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Python
- License
- MIT
- Cost to run
- Requires your model API key (OpenRouter or other provider)
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
- 20.2k
- Tracked growth
- +4.1%
- Maturity
- ●●●●●
- Last commit
- 4d 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 | DeepCode | 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. | ●●●●● Whole-repo analysis | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Permission & validation | ●●●●● Basic config filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Extensible skills & hooks | ●●●●● YAML config |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● BYO API key | ●●●●● Your API key |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Provider-agnostic (BYOK) | ●●●●● Any BYO model |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Config + API key | ●●●●● One-click demo |
Which one to pick
Pick DeepCode if…
Autonomous test-driven loops — pick DeepCode when you want an agent that plans, delegates across parallel workers, and iterates on a real repository until the project's tests are green.
- Context depth: Whole-repo analysis (5/5 against 3/5)
- Customization: Extensible skills & hooks (5/5 against 3/5)
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.
- Setup ease: One-click demo (5/5 against 3/5)
What people want from each one
HKUDS/DeepCode
Hacker News: DeepCode: Open Agentic Coding drew 18 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 DeepCode better than SWE-agent?
They split the axes: DeepCode leads on context depth and customization, SWE-agent on setup ease. DeepCode is worth picking when autonomous test-driven loops — pick DeepCode when you want an agent that plans, delegates across parallel workers, and iterates on a real repository until the project's tests are green.
Which of DeepCode and SWE-agent keeps my code private?
DeepCode: BYO API key (3/5). SWE-agent: Your API key (3/5).
What does each one cost to run?
DeepCode: Requires your model API key (OpenRouter or other provider). SWE-agent: Your API key (cloud LMs).
Full profiles: HKUDS/DeepCode and SWE-agent/SWE-agent. Everything else in Autonomous SWE agents.