OSS Radar

code-review-graph alternatives

tirth8205/code-review-graph (32k stars, +975 this week): Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters… Why it matters: relevant if AI is part of your coding workflow.

Below are 12 other Coding agents repos tracked by OSS Radar that share at least two GitHub topics with code-review-graph, ordered by how many topics overlap, then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

  1. Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Why it matters: relevant if AI is part of your coding workflow.

    7.8k stars · Go · shared topics: ai-coding, claude-code, code-review, llm, mcp

  2. 2. aoci-spec/aoci-code

    +140/wkest.

    A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Why it matters: relevant if AI is part of your coding workflow.

    1.6k stars · Go · shared topics: ai-coding, claude-code, llm, mcp

  3. 3. mksglu/context-mode

    +5k/wkest.

    Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing… Why it matters: relevant if AI is part of your coding workflow.

    30k stars · TypeScript · shared topics: claude, claude-code, mcp

  4. 4. Harvil1/codeAgent

    +756/wkest.

    CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and… Why it matters: relevant if AI is part of your coding workflow.

    702 stars · Python · shared topics: llm, mcp, python

  5. Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT. Why it matters: relevant if AI is part of your coding workflow.

    18k stars · Python · shared topics: claude-code, llm, mcp

  6. AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning… Why it matters: relevant if AI is part of your coding workflow.

    48k stars · Python · shared topics: ai-coding, claude-code, mcp

  7. 7. openqodex/openqodex

    +196/wkest.

    Open source code review that runs in your coding agent before you push. Scanners plus a separate AI reviewer, on your own login, no key. Why it matters: relevant if AI is part of your coding workflow.

    709 stars · TypeScript · shared topics: claude-code, code-review, static-analysis

  8. A builder, not just a researcher. Agent skills that turn top-grossing app patterns into native-quality mobile screens. Why it matters: relevant if AI is part of your coding workflow.

    2.9k stars · shared topics: claude, claude-code, mcp

  9. Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Why it matters: relevant if AI is part of your coding workflow.

    348 stars · Shell · shared topics: claude-code, code-review, llm

  10. A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model. Why it matters: relevant if AI is part of your coding workflow.

    391 stars · Python · shared topics: claude-code, llm, python

  11. 11. QwenLM/qwen-code

    +119/wkest.

    An open-source AI coding agent that lives in your terminal. Why it matters: relevant if AI is part of your coding workflow.

    29k stars · TypeScript · shared topics: ai-coding, llm, mcp

  12. 12. yetone/magpie

    +6.4k/wkest.

    Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar. Why it matters: relevant if AI is part of your coding workflow.

    13k stars · Go · shared topics: claude-code, llm

More: all trending Coding agents repos · compare code-review-graph with the top 2