SWE-agent vs symphony
The two are close in size: 20.2k stars for SWE-agent, 27.0k for symphony. Over the days we have tracked them SWE-agent moved +4.1% and symphony +7.9%, so symphony is growing faster right now.
SWE-agent leads on model freedom and setup ease. symphony 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
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)
Orchestrates isolated, autonomous implementation runs so teams manage work instead of supervising individual coding agents.
- Stars
- 27.0k
- Tracked growth
- +7.9%
- Maturity
- ●●●●●
- Last commit
- 16d ago
- Language
- Elixir
- License
- Apache-2.0
- Cost to run
- Self-hosted — runs on your infrastructure
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 | SWE-agent | symphony |
|---|---|---|
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 + related files | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic config filters | ●●●●● Human acceptance gating |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● YAML config | ●●●●● Minimal config |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Your API key | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Any BYO model | ●●●●● Fixed provider |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-click demo | ●●●●● Manual setup required |
Which one to pick
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.
- Model freedom: Any BYO model (5/5 against 1/5)
- Setup ease: One-click demo (5/5 against 3/5)
Pick symphony if…
Self-hostable — use Symphony when you want an on-prem orchestration that spawns isolated agent runs, produces PRs and CI proof-of-work, and reduces hands-on agent supervision.
What people want from each one
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.
openai/symphony
Hacker News: Show HN: Symphony – Use GPT-4 to call functions in sequence drew 93 points and 33 comments.
Questions people ask
Is SWE-agent better than symphony?
SWE-agent leads on model freedom and setup ease. symphony does not take any axis by a clear margin. SWE-agent is worth picking when 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.
Which of SWE-agent and symphony keeps my code private?
SWE-agent: Your API key (3/5). symphony: Self-hostable (4/5).
What does each one cost to run?
SWE-agent: Your API key (cloud LMs). symphony: Self-hosted — runs on your infrastructure.
Full profiles: SWE-agent/SWE-agent and openai/symphony. Everything else in Autonomous SWE agents.