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.
One SQL interface over APIs, files, and live sources — built for agents.
| Date | Stars |
|---|---|
| 2026-07-31 | 5021 |
| 2026-08-02 | 5021 |
| 2026-08-05 | 5005 |
| 2026-08-13 | 4996 |
| 2026-08-18 | 4990 |
| 2026-08-19 | 4988 |
| 2026-08-20 | 4985 |
| 2026-08-21 | 4983 |
| 2026-08-22 | 4983 |
| 2026-08-23 | 4979 |
| 2026-08-24 | 4976 |
| 2026-08-25 | 4975 |
| 2026-08-26 | 4976 |
| 2026-08-27 | 4977 |
| 2026-08-28 | 4975 |
| 2026-08-29 | 4973 |
| 2026-08-30 | 4971 |
| 2026-08-31 | 4969 |
| 2026-09-01 | 4967 |
| 2026-09-02 | 4965 |
| 2026-09-03 | 4961 |
| 2026-09-04 | 4959 |
| 2026-09-05 | 4958 |
| 2026-09-06 | 4956 |
| 2026-09-07 | 4953 |
| 2026-09-08 | 4952 |
| 2026-09-09 | 4953 |
| 2026-09-10 | 4951 |
| 2026-09-11 | 4952 |
| 2026-09-12 | 4953 |
| 2026-09-13 | 4948 |
| 2026-09-14 | 4946 |
| 2026-09-15 | 4945 |
| 2026-09-16 | 4945 |
| 2026-09-18 | 4946 |
| 2026-09-19 | 4945 |
| 2026-09-20 | 4943 |
Today
-2 stars today
This week
-5 stars this week
This month
-40 stars this month
Momentum
35.0
growth rate 0.00%/day
 [](https://github.com/withcoral/coral/actions/workflows/validate.yml) [](https://github.com/withcoral/coral/releases) [](./LICENSE) [](https://withcoral.com/docs) [](https://withcoral.com/discord) [](https://deepwiki.com/withcoral/coral) Coral is a single query interface for agents calling data source APIs. Agents make fewer, more precise tool calls with Coral than they do with per-source MCP servers, CLI tools, or API wrappers. For agent read tasks, SQL has a structural advantage when a question needs more than one API call: it avoids paginating through large results, returns tabular rows instead of sprawling JSON, brings back only the columns you asked for, and correlates across sources in a single statement. Everything is local: your data, credentials, and usage history never leave your machine. [](https://github.com/withcoral/coral/releases/latest/download/coral-desktop-mac-universal.dmg) [](https://github.com/withcoral/coral/releases/latest/download/coral-desktop-linux-x86_64.AppImage) [](https://github.com/withcoral/coral/releases/latest/download/coral-desktop-win-x64.exe) Coral ships as a desktop app on macOS, Linux, and Windows. For servers and automation, use the [CLI](#cli-quickstart). ## Get started 1. **Install Coral.** Use a download above, or see [all installation options](https://withcoral.com/docs/getting-started/installation). 2. **Add your sources.** Connect GitHub, Slack, Datadog, and other [bundled sources](https://withcoral.com/docs/reference/bundled-sources) from the sources page. Coral only fetches data from sources you connect. 3. **Connect your agents over MCP.** The app exposes an MCP server over stdio. Point Claude Code, Codex, Cursor, or VS Code at it — see [Use Coral over MCP](https://withcoral.com/docs/guides/use-coral-over-mcp). Then ask your agent a question about your data:  ## Why Coral Most agent workflows access company data one tool at a time. That works, but it tends to create: - too many tool calls - repeated auth, pagination, and retry logic - poor cross-source reasoning - high token traffic - brittle glue code and prompts Coral gives agents one query interface instead: - query multiple live sources through SQL - keep workflows inspectable and scriptable - expose the same runtime over MCP - answer cross-source questions without stitching tools together by hand We benchmarked Coral against direct provider MCPs (Datadog, Sentry, Linear, Slack, and GitHub) for a diverse set of 82 real-world AI tasks using Claude Opus 4.6. Key findings: 1. **Widespread impact on performance**. Across all tasks, Claude was 20% more accurate and 2x more cost efficient using Coral than using direct provider MCPs. With Coral, Claude also had 42% lower latency. 2. **
Excerpt of 13,200 characters
Read on GitHub
185
116
111
99
62
45
40
26
21
18
17
16
15
14
Arnav Kumar
13
Andrea Ambu · United Kingdom
13
Jishanahmed AR Shaikh (JARS) · India
13
12
12
8
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1973370a5d2946bc, llm:description: 'One SQL interface over APIs, files, and live sources — built for agents.' language: Rust
matched fp:1973370a5d2946bc, llm:description: 'One SQL interface over APIs, files, and live sources — built for agents.' language: Rust
matched fp:1973370a5d2946bc, llm:description: 'One SQL interface over APIs, files, and live sources — built for agents.' language: Rust