| --- |
| license: other |
| tags: |
| - code |
| - agent |
| - software-engineering |
| - autonomous |
| - swe-bench |
| - bug-fixing |
| - pull-request |
| language: |
| - en |
| - code |
| pipeline_tag: text-generation |
| --- |
| |
| # Daniel — Autonomous AI Software Engineer |
|
|
| **Daniel** is an autonomous AI software engineer built by [Cognitive AI](https://www.cognitivedaniel.com). It reads your codebase, writes code, runs tests, and opens pull requests — without you doing anything manually. |
|
|
| 🔗 **Try it:** [cognitivedaniel.com](https://www.cognitivedaniel.com) | 📊 **Benchmark:** [Daniel vs Devin](https://www.cognitivedaniel.com/devin-alternative) |
|
|
| --- |
|
|
| ## Benchmark results (v7, October 2026) |
|
|
| Daniel was tested head-to-head against Devin on 6 real bugs from popular open-source projects. Both agents received identical prompts. Each PR was graded by the project's own hidden test suite. |
|
|
| | Metric | Daniel | Devin | |
| |--------|--------|-------| |
| | Pass rate | **6/6 (100%)** | 6/6 (100%) | |
| | Total cost | **$1.45** | $4.91 | |
| | Total time | 12m 33s | 12m 12s | |
| | Cost per resolved bug | **$0.24** | $0.82 | |
|
|
| **Daniel is 70% cheaper than Devin at the same pass rate.** |
|
|
| Dataset: [cognitivedaniel/daniel-benchmark-v1](https://huggingface.co/datasets/cognitivedaniel/daniel-benchmark-v1) |
|
|
| --- |
|
|
| ## How Daniel works |
|
|
| Daniel uses a **4-turn agentic loop**: |
|
|
| 1. **Analyze** — reads the issue, the failing tests, and the relevant code |
| 2. **Implement** — makes the minimal code change to fix the bug |
| 3. **Test** — runs the project's existing test suite to verify the fix |
| 4. **PR** — opens a pull request with a clear description |
|
|
| The loop runs on Anthropic's Claude API. Daniel never opens a PR it hasn't verified against your tests. |
|
|
| --- |
|
|
| ## Supported languages |
|
|
| - Python, JavaScript, TypeScript (primary) |
| - Java, Go, Rust (via Multi-SWE-bench tier, in testing) |
|
|
| --- |
|
|
| ## Integrations |
|
|
| - GitHub (repos, issues, PRs) |
| - Jira (coming soon) |
| - Slack (coming soon) |
| - Run locally on any folder with one command |
|
|
| --- |
|
|
| ## Pricing |
|
|
| | Plan | Price | Tasks/month | |
| |------|-------|-------------| |
| | Starter | $20/mo | 20 | |
| | Pro | $100/mo | 200 | |
| | Enterprise | $500/mo | Unlimited | |
|
|
| --- |
|
|
| ## Links |
|
|
| - 🌐 [cognitivedaniel.com](https://www.cognitivedaniel.com) |
| - 📊 [Benchmark page](https://www.cognitivedaniel.com/devin-alternative) |
| - 💻 [GitHub](https://github.com/2badagoldman/cognitive-daniel) |
| - 🐦 [Twitter / X](https://x.com/CognitiveDaniel) |
|
|
| --- |
|
|
| ## Citation |
|
|
| If you use Daniel's benchmark results in your research: |
|
|
| ```bibtex |
| @misc{cognitive-ai-daniel-2026, |
| title={Daniel: Autonomous AI Software Engineer — Public Benchmark v1}, |
| author={Cognitive AI}, |
| year={2026}, |
| url={https://www.cognitivedaniel.com/devin-alternative}, |
| note={Dataset: huggingface.co/datasets/cognitivedaniel/daniel-benchmark-v1} |
| } |
| ``` |
|
|
