withcoral /coral

Execution rails for agents. Equip your AI to work with sensitive enterprise systems. Give agents precise permissions and custom tools that work faster with fewer tokens.

★ 4,935⑂ 223👁 14⑃ 2,377● 706▤ 46
RustApache-2.0Created 2026-04-03withcoral.com
Download: v1.8.0v1.8.0 ↓1.8.02026-11-13
-2
Daily
4,935
stars
223
forks
14
watchers
2,377
prs
706
issues
46
releases

README

!Coral, with engraved orange corals

 Coral

Execution rails for agents.

Coral gives your agents execution rails for work with sensitive enterprise
systems. It's self-hosted, open source, and you can use it with any agent and
any system with an API.

Control each call, not just each tool. Most agent setups decide only which
MCP tools an agent can see. That is all or nothing: if an agent can call
update_record, it can update any record in any way the tool allows. Coral
checks every call against your policy before it reaches the system. You allow
it, block it, or require a person to approve that exact call and its
arguments.

Less duplicated agent work. Agents start every task from scratch. They
re-read tool schemas, retry failed calls, and spend tokens rewriting code for
steps they got right yesterday. With Coral, agents save the code that worked
as custom tools they call again in one step, and workspace owners can share
them with the whole team.

Coral is used by thousands of developers at more than 450 companies for
safer, more efficient agent work in customer support, SecOps, business
intelligence, SRE, and more.






Quickstart ·
Download

In this example, an agent posts unreviewed PRs to Slack for the first time. The
agent searches for the GitHub and Slack tools and writes code that calls them.
It isn't allowed to post to Slack without approval, so the user approves the
post. The agent then saves its code as a custom tool. The next day, the agent
runs the same task by calling that custom tool.

!In Claude Code, an agent posts unreviewed pull requests to Slack. It searches Coral for the GitHub and Slack tools, writes code that calls them, and waits for approval before posting. The Coral UI then shows the run, who approved it, and the custom tool the agent saved. The next day, the same request runs by calling that custom tool. A final card compares the two days: 35% fewer tokens and 31% faster, in line with our benchmarks.

 Get started

1. Install Coral.
    - For yourself: download the desktop app for macOS, Linux, or Windows
      from the download page.
    - For your team: run a shared server
      with Docker Compose or Kubernetes.
2. Add a provider. A provider is one service your agents can use, such as
   GitHub or Linear. Pick one from the catalog, or bring your own OpenAPI
   document or MCP server. By default, tools that read data run right away and
   everything else needs your approval. See
   Add a provider.
3. Connect your agent. Copy your workspace's MCP URL from the Coral UI and
   add it to your MCP client:

    bash
    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.

4. Ask a question. Ask your agent something that uses that provider, such
   as "What are my open pull requests?" Once a task works, your agent saves it
   as a custom tool it can call in

Top issues

Latest release

v1.8.0 v1.8.0 2026-11-13
1.8.0 (2026-11-13)


 Features

 credentials: let operators define Secret Stores (2934) (4bb1f75)
 credentials: let Organization Owners grant Secret Stores to Workspaces (2955) (bbe8ba7)
 credentials: read a shared Account's Credential Fields from a Secret Store (2956) (9b4502e)
 credentials: read Credential Fields from a Vault or OpenBao KV v2 Secret Store (3082) (f551581)
 credentials: read Credential Fields from environment variables with an env Secret Store (3080) (b8d236f)
 credentials: show saved Secret References, and set them when adding a Provider (2964) (1147b4f)


 Bug Fixes

 ui: m

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON