← Open Source
withcoral

coral

The execution layer for AI agents. Act across more of your systems with precise controls: safer, faster and more efficient than MCP tools and gateways.

AI EngineeringGive agent toolsGive agent knowledgeRust
Open on GitHub
Momentum
+0stars in 24 hours0.0%
4.94k
Stars
223
Forks
+-4
This week
67
Contributors
Created 2026-04-03 · Updated 2026-10-16 · #7484 today
Top developers

withcoral/coral is ranked 7,484 with 4,938 stars.

Same-category comparison

withcoral/coral is ranked 7,484 among these 8 peers; 1rgs/jsonformer is ranked 7,483.

Same-category comparison
NameRankMetrics
rafaelpadilla/Object-Detection-Metrics7,454
Language:
Python
Stars:
5,105
Forks:
1,025
Description:
Most popular metrics used to evaluate object detection algorithms.
ag2ai/ag27,475
Language:
Python
Stars:
4,997
Forks:
745
Description:
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x.
microsoft/poml7,477
Language:
TypeScript
Stars:
4,969
Forks:
260
Description:
Prompt Orchestration Markup Language.
1rgs/jsonformer7,483
Language:
Jupyter Notebook
Stars:
4,938
Forks:
181
Description:
A Bulletproof Way to Generate Structured JSON from Language Models.
SolaceLabs/solace-agent-mesh7,491
Language:
Python
Stars:
4,914
Forks:
275
Description:
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.
aipotheosis-labs/aci7,492
Language:
Python
Stars:
4,912
Forks:
488
Description:
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
PennyroyalTea/gibberlink7,493
Language:
TypeScript
Stars:
4,911
Forks:
400
Description:
Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents.
thunlp/OpenPrompt7,497
Language:
Python
Stars:
4,904
Forks:
478
Description:
An Open-Source Framework for Prompt-Learning.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageRust
CategoryAI Engineering
SubcategoryGive agent tools, Give agent knowledge
KeywordsAgent-ready APIs, Databases, MCP, Retrieval
Stars4,938
Forks223
Contributors67
Created date2026-04-03
Updated date2026-10-16
Stars in 1 day0
Stars in 7 days-4
Rank7,484
Previous rank7,623
Rank change139
7-day stars rank18,711
Previous 7-day stars rank18,493
7-day stars rank change-218
Total stars rank2,840
Previous total stars rank2,835
Total stars rank change-5
README summary

Coral **One MCP server for every service your agents use, with your credentials and your rules. ** Agents write short TypeScript programs. Coral runs them in a sandbox, adds the credentials, and checks every call against your policy. Why Coral Connecting an agent to many services usually means many MCP servers, a token pasted into each one, and every tool definition loaded into every prompt. Coral replaces that with one server: **Smaller context, fewer round trips. ** The agent searches for the

operations it needs instead of loading them all up front. It then sends one program that can call several operations and return only the fields the answer needs. ** When a program works, the agent saves it as a function. The next time, it calls that function in one step instead of finding the operations and writing the program again. Saved functions are typed and appear in search alongside provider operations. ** Coral stores your tokens and adds them to each call

. Programs run in an isolated sandbox with no secrets, no network access, and no imports. ** Set each operation to allowed, approval required, or disabled. A call that needs approval waits until a person approves it. ** Review each program and the calls it made in the Coral UI. ** Run Coral on your laptop or on your own server. Your data, credentials, and usage history stay with you. Coral includes setup recipes for GitHub, Linear, Jira, Notion, Gmail, Stripe, Datadog, Sentry, HubSpot

, and more. You can add any service that has an OpenAPI document or an MCP server. ** Download the desktop app for macOS, Linux, or Windows from the releases page, or run a shared server for your team. ** A provider is one service your agents can use. Pick one from the catalog, or bring your own OpenAPI document or MCP server. ** Each workspace in Coral has its own MCP URL. Copy it from the Coral UI and add it to your

MCP client: Now ask your agent something that needs that provider, such as "What are my open pull requests? " Setup guides and the configuration reference are at withcoral. How Coral works The agent searches for the operations it can use and reads their TypeScript signatures. This one finds open pull requests that have no reviewer and posts them to Slack: Coral adds the credentials and checks each call against your policy. If posting to Slack requires approval, the run pauses

there until you approve it. Only the pull request numbers go back to the agent, not the full GitHub response. Once this works, the agent can save it as a function, and later programs call it as . To learn about providers, accounts, policy, and workspaces, read Concepts. 0 replaces the SQL interface with TypeScript programs. It is a rewrite and starts from fresh state: it does not convert what 0. x stored, and it tells you at startup if it

finds 0. Development To run Coral from a checkout, follow the development guide. Community Ask questions, share ideas, and show

Frequently asked questions

How many stars and forks are recorded?

withcoral/coral has 4,938 stars and 223 forks.

What is the repository rank?

withcoral/coral is ranked 7,484.

What language and category are recorded?

withcoral/coral has 4,938 stars, uses Rust and belongs to AI Engineering.

Which repository is closest in rank?

withcoral/coral is compared with 1rgs/jsonformer, ranked 7,483 with 4,938 stars.

README

Coral

One MCP server for every service your agents use, with your credentials and your rules. Agents write short TypeScript programs. Coral runs them in a sandbox, adds the credentials, and checks every call against your policy.

Why Coral

Connecting an agent to many services usually means many MCP servers, a token pasted into each one, and every tool definition loaded into every prompt. Coral replaces that with one server:

  • Smaller context, fewer round trips. The agent searches for the operations it needs instead of loading them all up front. It then sends one program that can call several operations and return only the fields the answer needs.
  • Agents build on what already worked. When a program works, the agent saves it as a function. The next time, it calls that function in one step instead of finding the operations and writing the program again. Saved functions are typed and appear in search alongside provider operations.
  • Agents never hold credentials. Coral stores your tokens and adds them to each call. Programs run in an isolated sandbox with no secrets, no network access, and no imports.
  • You decide what runs. Set each operation to allowed, approval required, or disabled. A call that needs approval waits until a person approves it.
  • Every run is recorded. Review each program and the calls it made in the Coral UI.
  • You host it. Run Coral on your laptop or on your own server. Your data, credentials, and usage history stay with you.

Coral includes setup recipes for GitHub, Linear, Jira, Notion, Gmail, Stripe, Datadog, Sentry, HubSpot, and more. You can add any service that has an OpenAPI document or an MCP server.

Get started

  1. Install Coral. Download the desktop app for macOS, Linux, or Windows from the releases page, or run a shared server for your team.

  2. Add a provider. A provider is one service your agents can use. Pick one from the catalog, or bring your own OpenAPI document or MCP server. See Add a provider.

  3. Connect your agent. Each workspace in Coral has its own MCP URL. Copy it from the Coral UI and add it to your MCP client:

    claude mcp add --scope user --transport http coral    # Claude Code
    codex mcp add coral --url                             # Codex
    

    For Cursor, VS Code, OpenCode, and other clients, see Connect an MCP client.

Now ask your agent something that needs that provider, such as "What are my open pull requests?"

Setup guides and the configuration reference are at withcoral.com/docs.

How Coral works

graph LR
    Agent["Your agent"] -->|"search, exec"| MCP["Coral MCP server"]
    You["You"] -->|"providers, policy, approvals"| UI["Coral UI"]

    subgraph Coral["Coral (your machine or server)"]
        MCP --> Run["Sandboxed program run"]
        UI --> Gate["Credentials and policy"]
        Run --> Gate
    end

    Gate --> GH["GitHub"]
    Gate --> SL["Slack"]
    Gate --> Own["Your OpenAPI or MCP service"]

The agent searches for the operations it can use and reads their TypeScript signatures. Then it sends Coral a short program. This one finds open pull requests that have no reviewer and posts them to Slack:

const { data: pulls } = await coral.providers.github.pulls.list({
    owner: "withcoral",
    repo: "coral",
    state: "open",
});

const unreviewed = pulls.filter((pull) => pull.requested_reviewers.length === 0);

await coral.providers.slack.chat.postMessage({
    channel: "#engineering",
    text: unreviewed.map((pull) => `#${pull.number} ${pull.title}`).join("\n"),
});

return unreviewed.map((pull) => pull.number);

Coral adds the credentials and checks each call against your policy. If posting to Slack requires approval, the run pauses there until you approve it. Only the pull request numbers go back to the agent, not the full GitHub response. Once this works, the agent can save it as a function, and later programs call it as coral.functions.().

To learn about providers, accounts, policy, and workspaces, read Concepts.

Upgrade from Coral 0.x

Coral 1.0 replaces the SQL interface with TypeScript programs. It is a rewrite and starts from fresh state: it does not convert what 0.x stored, and it tells you at startup if it finds 0.x state. See Upgrade from Coral 0.x.

Development

To run Coral from a checkout, follow the development guide.

Community

Ask questions, share ideas, and show what you built in our Discord or on GitHub issues.

Security

Do not report security issues in public issues or pull requests. See SECURITY.md.

License

Coral is licensed under the Apache License 2.0. See LICENSE.

Nearby in the ranking
Similar items