deer-flow vs ECC
ECC is much bigger: 249.0k stars against 81.4k. Over the days we have tracked them deer-flow moved +5.4% and ECC +8.1%, so ECC is growing faster right now.
ECC leads on context depth and noise control. deer-flow 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
Orchestrates long-horizon, multi-agent research workflows with sandboxed file-system sandboxes, subagents, memory and replay tools for reproducible deep-research tasks.
- Stars
- 81.4k
- Tracked growth
- +5.4%
- Maturity
- ●●●●●
- Last commit
- 5h ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key or self-hosted
A harness-native, cross-harness agent operating system that bundles skills, session/state memory, verification loops, and AgentShield for production multi-harness workflows.
- Stars
- 249.0k
- Tracked growth
- +8.1%
- Maturity
- ●●●●●
- Last commit
- 16h ago
- Language
- JavaScript
- License
- MIT
- Cost to run
- Free OSS; optional Pro GitHub App ($19/seat/mo) + your model/API costs
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 | deer-flow | ECC |
|---|---|---|
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 | ●●●●● Whole-repo analysis |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters | ●●●●● Severity gating |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Extensive config | ●●●●● Extensive configs |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Fully local |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● BYOK & local | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Interactive setup | ●●●●● Config + API key |
Which one to pick
Pick deer-flow if…
Extensible tooling — pick DeerFlow when you need a self-hostable, highly configurable super-agent harness that runs multi-step, sandboxed research and coding workflows with local model support.
Pick ECC if…
Production-ready — pick ECC when you need a self-hostable, operator-grade agent harness with built-in skills, memory, verification, and a GitHub App for PR audits.
- Context depth: Whole-repo analysis (5/5 against 3/5)
- Noise control: Severity gating (5/5 against 3/5)
What people want from each one
bytedance/deer-flow
Hacker News: Has Anyone Tried Deerflow? drew 4 points and 0 comments.
Questions people ask
Is deer-flow better than ECC?
ECC leads on context depth and noise control. deer-flow does not take any axis by a clear margin. deer-flow is worth picking when extensible tooling — pick DeerFlow when you need a self-hostable, highly configurable super-agent harness that runs multi-step, sandboxed research and coding workflows with local model support.
Which of deer-flow and ECC keeps my code private?
deer-flow: Self-hostable (4/5). ECC: Fully local (5/5).
What does each one cost to run?
deer-flow: Your API key or self-hosted. ECC: Free OSS; optional Pro GitHub App ($19/seat/mo) + your model/API costs.
Full profiles: bytedance/deer-flow and affaan-m/ECC. Everything else in Multi-agent orchestration.