head to head · open source
code-review-graph vs agentsys
code-review-graph has 31,548 GitHub stars, 2,870 forks, 163 open issues and last shipped yesterday. agentsys has 986 stars, 115 forks, 0 open issues and last shipped 5 days ago. code-review-graph leads on adoption by 3,100% (31,548 vs 986 stars). code-review-graph is written in Python under MIT; agentsys is written in JavaScript under MIT. code-review-graph has attracted 9% as many forks as stars, agentsys 12%. code-review-graph was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 3 topic tags (claude, claude-code, code-review), 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.
← all 8884 open source comparisons
Side by side
| code-review-graph | agentsys | |
|---|---|---|
| GitHub stars | ★ 32K | ★ 986 |
| License | MIT | MIT |
| Written in | Python | JavaScript |
| Last push | 2026-09-17 | 2026-09-13 |
| Forks | ⑂ 2.9K | ⑂ 115 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick code-review-graph if
- You weight community size — 32K stars and counting
- You want the MIT license terms
- Your stack matches Python
- You value the larger contributor base for long-term maintenance
pick agentsys if
- You want the agentsys feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches JavaScript
- You evaluated both and agentsys fits your workflow better
About code-review-graph
code review graph is a local first code intelligence graph for MCP and the command line that parses a repository with Tree sitter into a persistent map of functions, classes, imports, calls, inheritance and test coverage, so AI coding assistants read only the files a review actually needs; it is aimed at developers and teams running AI coding tools against large repositories where repeated full codebase reads waste tokens.
read the full code-review-graph overview →
About agentsys
AgentSys is a modular runtime and orchestration system for AI agents — a marketplace and installer that ties together 24 plugins, 49 agents, and 44 skills into gated development pipelines — built for developers and teams working in Claude Code, Codex CLI, OpenCode, Cursor, or Kiro who want the work around code generation automated, not only the code generation itself.
read the full agentsys 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 agentsys more popular?
code-review-graph has 31,548 GitHub stars and agentsys has 986. code-review-graph has the larger community by that measure.
Are code-review-graph and agentsys free?
Both are open source. code-review-graph is licensed under MIT and agentsys under MIT. Neither carries a licence fee.
What is the difference between code-review-graph and agentsys?
code-review-graph is written in Python and agentsys in JavaScript. 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 agentsys?
Choose code-review-graph if you want the larger community (31,548 stars) or its MIT licence terms. Choose agentsys if its feature set, stack or MIT licence fits better. Both are self-hostable.