head to head · open source

code-review-graph vs roam-code

code-review-graph has 32,563 GitHub stars, 2,964 forks, 163 open issues and last shipped 5 days ago. roam-code has 516 stars, 50 forks, 12 open issues and last shipped 3 days ago. code-review-graph leads on adoption by 6,211% (32,563 vs 516 stars). code-review-graph is written in Python under MIT; roam-code is written in Python under Apache-2.0. code-review-graph has attracted 9% as many forks as stars, roam-code 10%. roam-code was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 3 topic tags (ai-coding, code-review, mcp), so they are genuine substitutes rather than adjacent tools.

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

code-review-graph ★ 33K roam-code ★ 516 category Developer Tools

← all 20902 open source comparisons

Side by side

code-review-graph roam-code
GitHub stars ★ 33K ★ 516
License MIT Apache-2.0
Written in Python Python
Last push 2026-10-29 2026-10-31
Forks ⑂ 3.0K ⑂ 50
Self-hosting Yes Yes
Data ownership Your server Your server

pick code-review-graph if

  • You weight community size — 33K stars and counting
  • You want the MIT license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full code-review-graph profile →

pick roam-code if

  • You want the roam-code feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches Python
  • You evaluated both and roam-code fits your workflow better

full roam-code profile →

About code-review-graph

code review graph Stop burning tokens. Start reviewing smarter. English 简体中文 日本語 한국어 हिन्दी Usage · Commands · FAQ · Troubleshooting · GitHub Action · Reproducing the benchmarks · Roadmap AI coding tools can end up re reading large parts of your codebase on review tasks. code review graph fixes that. It builds a structural map of your code with Tree sitter, tracks changes incrementally, and gives your AI assistant precise context via MCP so it reads only what matters. Quick Start One command sets up everything. install detects which AI coding tools you have, writes the correct MCP configuration for each one…

read the full code-review-graph overview →

About roam-code

roam code Local code analysis and ready to run checks for coding agents. Roam gives your agent a reusable codebase index, pattern findings, candidate algorithmic alternatives, and checks it can call as it works. It can investigate code and evaluate changes without building each analysis from scratch. Runs on your machine · free and open source · no account or API key for local analysis · no automatic source code or telemetry upload 287 commands · 246 MCP tools (17 in the default core preset) · 28 languages Connect your agent · Try a task · Documentation · Explore the code map Why Roam is different Your agent can…

read the full roam-code overview →

More in Developer Tools

Related comparisons

More Version Control & Collaboration projects

Compare either of these against the rest of the Version Control & Collaboration field.

Frequently asked questions

Is code-review-graph or roam-code more popular?

code-review-graph has 32,563 GitHub stars and roam-code has 516. code-review-graph has the larger community by that measure.

Are code-review-graph and roam-code free?

Both are open source. code-review-graph is licensed under MIT and roam-code under Apache-2.0. Neither carries a licence fee.

What is the difference between code-review-graph and roam-code?

code-review-graph is written in Python and roam-code 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, code-review-graph or roam-code?

Choose code-review-graph if you want the larger community (32,563 stars) or its MIT licence terms. Choose roam-code if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.