Devika vs SWE-agent
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
Open-source experimental AI agent that tries to plan, research, and write software from a plain-language goal.
Open source · MIT
An AI agent that tries to fix GitHub issues automatically, using the language model you choose.
The short answer
Choose Devika if you need…
- Developers curious about how autonomous coding agents work and who want to experiment with one
- Hobbyists who want to try an agent on small, low-stakes coding tasks
- Contributors who want to help build an early-stage agent project
- People who already have API keys for supported models and want a self-hosted option
Choose SWE-agent if you need…
- Researchers studying autonomous coding agents or running SWE-bench experiments
- Developers who want to experiment with an LLM attempting issue fixes in their own repositories
- Students learning how agent-computer interfaces work, since the README describes it as simple and hackable
- People who want a configurable agent controlled by a single YAML file
Side-by-side
| Devika | SWE-agent | |
|---|---|---|
| Type | AI model / agent | AI model / agent |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 19.6k | 20.7k |
| Setup difficulty | Intermediate | Intermediate |
| How you get it | Clone and build from source | Clone and build from source |
| Main language | Python | Python |
| Last code update | 14 months ago | 10 days ago |
What each one is
Devika
Devika is an experimental AI software engineer. You give it a high-level task in a chat interface, and it tries to break the task into steps, search the web for information, and write code. It works with several large language models, including Claude, GPT-4, Gemini, Mistral, Groq, and local models via Ollama. The project is modeled after Devin by Cognition AI and is an open-source attempt at a similar idea.
SWE-agent
SWE-agent takes a GitHub issue and lets a language model you pick (the README mentions GPT-4o and Claude Sonnet 4 as examples) use tools to try to fix it in a real repository. It is also described as usable for offensive cybersecurity (capture-the-flag) challenges and custom coding tasks. It is a research project from Princeton and Stanford, and its README says its main development has moved to the simpler mini-SWE-agent.
Best for
Devika
- Developers curious about how autonomous coding agents work and who want to experiment with one
- Hobbyists who want to try an agent on small, low-stakes coding tasks
- Contributors who want to help build an early-stage agent project
- People who already have API keys for supported models and want a self-hosted option
SWE-agent
- Researchers studying autonomous coding agents or running SWE-bench experiments
- Developers who want to experiment with an LLM attempting issue fixes in their own repositories
- Students learning how agent-computer interfaces work, since the README describes it as simple and hackable
- People who want a configurable agent controlled by a single YAML file
Strengths
Devika
- Open source under the MIT License, so the code can be read, modified, and reused
- Supports many model providers, including local models through Ollama
- Active public project with an issue tracker, discussions, and a Discord community
SWE-agent
- The README reports state-of-the-art results on SWE-bench among open-source projects
- Configuration is handled by a single YAML file and the README says it is fully documented
- MIT licensed with a public docs site, Slack, and a Codespaces option to try it in a browser
Not ideal for
Devika
- Anyone needing reliable production code, since the README says the project is in a very early, experimental stage with many unimplemented or broken features
- Non-technical users who cannot set up Python, Node.js, and API keys
- Teams that need a supported product with documentation and guarantees, since no release is listed
SWE-agent
- Teams wanting the project's actively recommended tool: the README says most development has moved to mini-SWE-agent, which it recommends instead
- Anyone needing a polished, finished product: the project is framed as research code
- People who cannot pay for or access a language model API, since the README assumes you bring your own model
Trade-offs
Devika
- The README states it is very early and experimental with many unimplemented or broken features
- Web research requires search API keys such as Bing or Google, adding setup work
- Setup involves several tools (uv, bun, Playwright, Python 3.10 or 3.11, Node.js 18+) and separate frontend and backend processes
SWE-agent
- The README says mini-SWE-agent has superseded it and is recommended instead going forward
- The EnIGMA cybersecurity mode currently points users to older version 0.7 rather than 1.0
- Results depend on the language model and API you supply; the README does not state costs or hardware needs
Getting started
Devika
Clone the repository
git clone https://github.com/stitionai/devika.gitEnter the project directory
cd devikaSWE-agent
Clone the repository
git clone https://github.com/SWE-agent/SWE-agent.gitFrequently asked questions
What is the difference between Devika and SWE-agent?
Devika: Open-source experimental AI agent that tries to plan, research, and write software from a plain-language goal. SWE-agent: An AI agent that tries to fix GitHub issues automatically, using the language model you choose. Devika suits developers curious about how autonomous coding agents work and who want to experiment with one, while SWE-agent suits researchers studying autonomous coding agents or running swe-bench experiments.
Are Devika and SWE-agent free?
Devika: Free and open source. SWE-agent: Free and open source.
Is Devika or SWE-agent more popular?
SWE-agent has more GitHub stars (20.7k) than Devika (19.6k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to Devika and SWE-agent?
Other options people compare them with include OpenHands, DeerFlow, Open SWE, RD-Agent, Ponytail.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.