head to head · open source

codegraph vs SWE-agent

codegraph has 71,514 GitHub stars, 4,598 forks, 526 open issues and last shipped 4 days ago. SWE-agent has 20,367 stars, 2,230 forks, 102 open issues and last shipped 6 days ago. codegraph leads on adoption by 251% (71,514 vs 20,367 stars). codegraph is written in C under MIT; SWE-agent is written in Python under MIT. codegraph has attracted 6% as many forks as stars, SWE-agent 11%. codegraph was the more recently maintained of the two, and both are self-hostable with no licence fee.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

codegraph ★ 72K SWE-agent ★ 20K category Developer Tools

← all 20902 open source comparisons

Side by side

codegraph SWE-agent
GitHub stars ★ 72K ★ 20K
License MIT MIT
Written in C Python
Last push 2026-09-16 2026-09-14
Forks ⑂ 4.6K ⑂ 2.2K
Self-hosting Yes Yes
Data ownership Your server Your server

pick codegraph if

  • You weight community size — 72K stars and counting
  • You want the MIT license terms
  • Your stack matches C
  • You value the larger contributor base for long-term maintenance

full codegraph profile →

pick SWE-agent if

  • You want the SWE-agent feature set and don't need the biggest community
  • You prefer the MIT license terms
  • Your stack matches Python
  • You evaluated both and SWE-agent fits your workflow better

full SWE-agent profile →

About codegraph

CodeGraph is a pre indexed code knowledge graph that runs locally and wires into AI coding agents — Claude Code, Cursor, Codex, Gemini, OpenCode, AntiGravity, Kiro, GitHub Copilot, and Hermes Agent — so those agents query a semantic map of the codebase instead of reading files one at a time.

read the full codegraph overview →

About SWE-agent

SWE agent is a Python, MIT licensed open source project in the AI assisted coding and agent ecosystem. It is an agent based model for developer tools that takes a GitHub issue and tries to automatically fix it using a chosen language model. The project is associated with NeurIPS 2024 and is maintained by researchers from Princeton University and Stanford University.

read the full SWE-agent overview →

More in Developer Tools

ECC ★ 263K react ★ 251K OpenCode ★ 209K vscode ★ 193K Langflow ★ 155K Supabase ★ 110K

Related comparisons

codegraph vs code-review-graph openclaw vs openhands openclaw vs paperclip hermes-agent vs pi hermes-agent vs openhands hermes-agent vs paperclip opencode vs pi opencode vs openhands opencode vs paperclip openclaw vs langflow ecc vs react ecc vs langflow react vs langflow ecc vs supabase react vs supabase n8n vs langflow ecc vs puppeteer react vs vscode react vs neovim react vs zed opencode vs neovim opencode vs zed vscode vs neovim vscode vs zed

More AI Assisted Coding projects

Compare either of these against the rest of the AI Assisted Coding field.

codegraph vs OpenCode codegraph vs pi codegraph vs OpenHands codegraph vs Paperclip codegraph vs rtk codegraph vs Orca codegraph vs Cline codegraph vs Aider codegraph vs Continue codegraph vs Tabby codegraph vs Grok Build codegraph vs T3 Code

Frequently asked questions

Is codegraph or SWE-agent more popular?

codegraph has 71,514 GitHub stars and SWE-agent has 20,367. codegraph has the larger community by that measure.

Are codegraph and SWE-agent free?

Both are open source. codegraph is licensed under MIT and SWE-agent under MIT. Neither carries a licence fee.

What is the difference between codegraph and SWE-agent?

codegraph is written in C and SWE-agent in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, codegraph or SWE-agent?

Choose codegraph if you want the larger community (71,514 stars) or its MIT licence terms. Choose SWE-agent if its feature set, stack or MIT licence fits better. Both are self-hostable.