7 alternatives to open-code-review
alibaba/open-code-review — Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), Ope (47,945 stars, Apache-2.0, ui, ai, integration).
These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It also serves 320 licence-cleared components from alibaba/open-code-review itself.
| # | Repo | Score | Licence | Stars |
|---|---|---|---|---|
| 1 | bytedance/deer-flow | 7.5 | MIT | 84,262 |
| 2 | 8treenet/goraven | 5.8 | Apache-2.0 | 816 |
| 3 | claw-eval/claw-eval | 5.0 | MIT | 779 |
| 4 | suyoumo/clawprobench | 5.9 | Apache-2.0 | 827 |
| 5 | aden-hive/hive | 5.1 | Apache-2.0 | 11,122 |
| 6 | kevinluosl/deepbot | 5.6 | MIT | 2,457 |
| 7 | the-open-agent/openagent | 5.7 | Apache-2.0 | 5,708 |
The alternatives in detail
-
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take
-
Open-source AI Agent platform for teams. Your agents don't just chat — they read files, run code, call APIs, and deliver results.score 5.8/10 · Apache-2.0 permissive · 816 stars · 378 components · search them
-
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.score 5.0/10 · MIT permissive · 779 stars · 361 components · search them
-
ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.score 5.9/10 · Apache-2.0 permissive · 827 stars · 2,434 components · search them
-
Multi-Agent Harness for Production AIscore 5.1/10 · Apache-2.0 permissive · 11,122 stars · 737 components · search them
-
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.score 5.6/10 · MIT permissive · 2,457 stars · 206 components · search them
-
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.orgscore 5.7/10 · Apache-2.0 permissive · 5,708 stars · 841 components · search them
Licence data: JustClaw-It's per-repo licence policy. Is open-code-review still maintained? Check it. Licence details: licence checker. Ranking data from 2026-10-27T23:04:12Z.
Want code like open-code-review without the licence risk? JustClaw-It is an MCP server with 1,449,000+ licence-cleared, quality-scored code components. Search is free; every result carries its licence and attribution.
Remote MCP endpoint: https://justclaw.it.com/mcp (API key auth). Works with Claude Code, Cursor,
Codex, Windsurf and other MCP clients. A one-line CLI installer (@justclaw-it/cli) is coming.