Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 285 commands, 244 MCP tools, change-safety gates, audit evidence, zero API keys.
| Date | Stars |
|---|---|
| 2026-07-31 | 501 |
| 2026-08-06 | 504 |
Today
+3 stars today
This week
— stars this week
This month
— stars this month
Momentum
47.0
growth rate 0.00%/day
<div align="center"> # roam-code **The local codebase intelligence layer that lets AI coding agents earn the right to change code — with evidence for what was checked.** [](https://pypi.org/project/roam-code/) [](https://github.com/Cranot/roam-code/stargazers) [](https://github.com/Cranot/roam-code/actions/workflows/roam-ci.yml) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/Apache-2.0) <sub>Credential-free · local analysis with no automatic source-code or telemetry upload · tamper-evident `ChangeEvidence` packets · Apache 2.0 · runs on your machine</sub> <!-- BEGIN auto-count:readme-headline-counts --> <sub>285 commands · 244 MCP tools (17 in the default `core` preset) · 28 languages</sub> <!-- END auto-count:readme-headline-counts --> <sub><a href="https://roam-code.com/pricing"><b>Paid layers →</b></a> <b>PR Replay</b> audit $2,500 Team / $6,000 Deep, available now · <b>Roam Review</b> from $99/mo flat — no per-seat pricing · <b>Roam Cloud</b> $19/repo/mo · Review and Cloud are early access. The CLI below is Apache 2.0 and free forever.</sub>  </div> --- **Jump to** — [Why Roam](#why-roam-is-different) · [Install](#install--first-four-commands) · [The Compiler](#the-compiler--your-agents-first-token-already-knows-the-answer) · [Core commands](#core-commands) · [MCP server](#mcp-server) · [AI-tool integration](#integration-with-ai-coding-tools) · [Roam Guard (PR gate)](#roam-guard-for-prs) · [Performance](#performance) · [Compare](#how-roam-compares) · [Pricing](#paid-layers-free-cli-stays-apache-20) · [FAQ](#faq) --- ## Why Roam is different [METR](https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/) and [FrontierCode](https://cognition.ai/blog/frontier-code) both point at the same gap: passing tests is not the same as mergeable code. Roam is an **agent-first CLI surface** that gives the agent local graph facts before it edits, gates risky changes, and emits scoped evidence after the run. In the agent/review tools surveyed as of 2026-06-12, the differentiator is this combination: - **Credential-free.** No account, no API key, no cloud login. `pip install` and run. - **Local analysis with an explicit network boundary.** Source parsing, indexes, findings, and evidence generation stay on the machine; Roam sends no automatic telemetry or update checks. A cold `tree-sitter-language-pack` grammar cache downloads one checksum-verified platform bundle and retains it locally. Additional network-capable commands and flags are opt-in and inventoried in [`docs/network-boundary.md`](docs/network-boundary.md), including their destinations and payload classes. - **Tamper-evident `ChangeEvidence` packets.** A Roam-guided change can compile into one portable packet — HMAC-chained run ledger + signed Code Graph Attestation + signed PR bundle — answering eight questions: *who acted, what authority existed, what context was read, what changed, what could break, what policy applied, what verified it, who accepted risk*. PR Replay maps those eight questions today: structural change/risk/policy axes are in scope, context and verification are partial, and missing identity/authority/approval evidence is disclosed instead of invented. Cursor logs the run; Roam records and verifies the evidence its producers captured. - **MCP runtime security at the wrapper boundary.** Every MCP response is scrubbed for secrets on egress, gated against the active mode (`re
Excerpt of 65,124 characters
Read on GitHub
2.1k
10
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b206f7b8dea24716, topic:mcp, topic:model-context-protocol, topic:mcp-server
matched fp:b206f7b8dea24716, topic:ai-coding, topic:code-review, topic:developer-tools