head to head · open source
codebase-memory-mcp vs Onlook
codebase-memory-mcp has 48,082 GitHub stars, 3,959 forks, 552 open issues and last shipped 2 days ago. Onlook has 27,108 stars, 2,139 forks, 380 open issues and last shipped 15 days ago. codebase-memory-mcp leads on adoption by 77% (48,082 vs 27,108 stars). codebase-memory-mcp is written in C under MIT; Onlook is written in TypeScript under Apache-2.0. codebase-memory-mcp has attracted 8% as many forks as stars, Onlook 8%. codebase-memory-mcp was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 3 topic tags (claude-code, codex, cursor), 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 20902 open source comparisons
Side by side
| codebase-memory-mcp | Onlook | |
|---|---|---|
| GitHub stars | ★ 48K | ★ 27K |
| License | MIT | Apache-2.0 |
| Written in | C | TypeScript |
| Last push | 2026-11-03 | 2026-10-21 |
| Forks | ⑂ 4.0K | ⑂ 2.1K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick codebase-memory-mcp if
- You weight community size — 48K stars and counting
- You want the MIT license terms
- Your stack matches C
- You value the larger contributor base for long-term maintenance
pick Onlook if
- You want the Onlook feature set and don't need the biggest community
- You prefer the Apache-2.0 license terms
- Your stack matches TypeScript
- You evaluated both and Onlook fits your workflow better
About codebase-memory-mcp
codebase memory mcp: local code intelligence for AI agents via MCP Understand your repository, from source code to the systems around it. codebase memory mcp is an MCP server that connects code, documentation, configuration, and infrastructure in a persistent local knowledge graph. Use it to find an unfamiliar feature, follow a call across services, trace a deployment back to its source, or assess which parts of a project a change could affect. Give your coding agent structural context through Model Context Protocol (MCP), or query the graph directly from the CLI. The MCP server is the core of the project. Its…
read the full codebase-memory-mcp overview →
About Onlook
Onlook The design tool for AI native designers — now in early access. Onlook makes designing on top of your codebase effortless. Craft exceptional experiences with AI in code. → Join the waitlist 👨💻👩💻👨💻 We're hiring engineers in SF! 👩💻👨💻👩💻 View Demo · Report Bug · Request Feature [![Discord][discord shield]][discord url] [![LinkedIn][linkedin shield]][linkedin url] [![Twitter][twitter shield]][twitter url] 中文 Español Deutsch français Português Русский 日本語 한국어 This is the open source visual editor that started Onlook (Next.js + Tailwind). The hosted product we're building next, for AI native…
read the full Onlook overview →
More in Developer Tools
Related comparisons
More Frameworks & Platforms projects
Compare either of these against the rest of the Frameworks & Platforms field.
Frequently asked questions
Is codebase-memory-mcp or Onlook more popular?
codebase-memory-mcp has 48,082 GitHub stars and Onlook has 27,108. codebase-memory-mcp has the larger community by that measure.
Are codebase-memory-mcp and Onlook free?
Both are open source. codebase-memory-mcp is licensed under MIT and Onlook under Apache-2.0. Neither carries a licence fee.
What is the difference between codebase-memory-mcp and Onlook?
codebase-memory-mcp is written in C and Onlook in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, codebase-memory-mcp or Onlook?
Choose codebase-memory-mcp if you want the larger community (48,082 stars) or its MIT licence terms. Choose Onlook if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.