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 |
| 2026-08-06 | 5005 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
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 gives agents a local-first SQL runtime over APIs, files, and other data
sources. Query it from the CLI, inspect schemas and tables, or expose the same
runtime over MCP so agents can use it without bespoke tool glue.
You can ask your agents complex questions about your data:
Or run SQL queries yourself:
## 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 with 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. **Highest impact on coding agent tasks**. Across the more complex tasks that typify coding agent workloads (multi-hop, higher post-processing), Claude was 31% more accurate and 3.4x more cost efficient with Coral.
3. **More neutral impact on simpler tasks**. For simpler AI tasks, such as raw fact retrieval from knowledge bases, the results were closer, with Claude 6% more accurate and 2% more cost efficient with Coral.
Full [benchmark report](https://withcoral.com/benchmarks).
## How Coral works
Coral sits between your agents and your data sources: your agents write SQL,
and Coral translates it into API calls or file reads, then returns a single
result set.
```mermaid
graph LR
Agent["You / your agent"] -->|SQL query| Coral["Coral (local)"]
Coral -->|Result rows| Agent
subgraph Sources["Installed sources"]
GH["github source<br/>(github.* tables)"]
LN["linear source<br/>(linear.* tables)"]
FS["file source<br/>(your_files.* tables)"]
end
Coral --> GH
Coral --> LN
Coral --> FS
subgraph Backing["Backing systems"]
GHAPI["GitHub API"]
LNAPI["Linear API"]
Disk["Local files"]
end
GH -.->|PAT / gh auth token| GHAPI
LN -.->|Personal API key| LNAPI
FS -.->|File path| Disk
```
**Sources.** A _source spec_ is a YAML file that declares how to reach an API
or local dataset and which tables and columns it exposes. A _source_ is that
spec plus the credentials and variables you configured for it. When you run
`coral source add github`, Coral installs the `github` source and exposes it
at query time as the `github` SQL schema, so tables like `github.issues` and
`github.pulls` become queryable. Start with the
[bundled sources](https://withcoral.com/docs/reference/bundled-sources) or
[write your own](https://withcoral.com/docs/guides/write-a-custom-source).
**Joins across sources.** Because every source appears as SQL tables, you can
`JOIN` across them in oneExcerpt of 10,756 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