by Phoebe Technology Limited

Coral review, pricing and verdict

Open-source, self-hosted gateway where agents write TypeScript programs to call tools under Allow, Ask or Block rules; about 5,000 GitHub stars.

Best for
Site reliability engineer
Not for
Operations manager who wants a visual no-code builder

Should you use Coral?

Pick Coral when agents must touch sensitive systems and you want per-operation approvals on infrastructure you control. It replaces hand-written API wrappers for each agent. The verdict: strong for engineering teams today, certified to ISO/IEC 27001:2022, though enterprise sign-on and audit logging are still coming and the benchmarks are the maker's own.

Agents save the programs that worked as custom tools, and each saved tool carries its own Allow, Ask or Block rule.

Saved custom tools and run traces accumulate inside a workspace, which makes leaving costly, but the gateway code is open source so the layer itself can be forked.

Also for

  • Platform engineer
  • Security engineer
Show 5 more
  • Site reliability engineers running an AI SRE agent
  • Platform engineers who give agents access to internal systems
  • Security operations engineers who need agents to act within approved groups
  • Support operations leads whose agent issues refunds
  • Data and business intelligence analysts building shared agent tools

Main trade-off

The enterprise controls a regulated buyer asks for first are not shipped yet.

Coral pricing

PlanMonthly priceWhat it includes
Open SourceFreeCoral tool execution layer, Agent permissions control plane, Shared agent workflows, Unlimited data sources, Unlimited agents, Unlimited queries
EnterpriseCustomEverything in Open Source, SAML SSO and SCIM provisioning, Advanced RBAC and agent policy controls, Immutable audit log, Bring your own secrets vault, Custom provider integrations

Open Source: free under the Apache 2.0 licence, self-hosted, with unlimited data sources, agents and queries; you bring your own LLM keys and your model provider bills you. Enterprise: custom pricing quoted on request, adding SAML SSO, SCIM, advanced RBAC, an immutable audit log and support SLAs; the README lists Enterprise as coming soon. Source: withcoral.com/pricing.

Before you commit

  • Model usage is billed by your own LLM provider, not by Coral.
  • A shared server means running an identity provider, a TLS reverse proxy and a database yourself.

What Coral does

Coral is an open-source, self-hosted AI gateway in the agent gateways category. Agents write short TypeScript programs that run in a V8 isolate, and Coral checks every call against Allow, Ask or Block policy before it adds credentials. The code is Apache 2.0 licensed and the latest release is 1.8.0.

  • Agent-written programs

    Agents call tools through short TypeScript programs that run sandboxed, so a program can only reach what Coral lets it call.

  • Allow, Ask or Block rules

    You set a rule for each provider tool and each custom tool, and an approval request shows the exact call and its arguments.

  • Saved custom tools

    A program that worked becomes a private tool the agent finds in the same search as provider tools, and an owner can share it workspace-wide.

  • Providers from OpenAPI or MCP

    Add a service from the catalog, an OpenAPI document or an MCP server, and agents find its tools in one search.

Show all 7 features
  • Per-user accounts

    A provider can run as the caller's own account, so teammates share tools without sharing API tokens.

  • Run traces

    Every run is attributed to the person or agent that started it and records the goal, the tools used and the outcome.

  • Desktop app or shared server

    The desktop app runs on macOS (Apple silicon), Windows (x64) and Linux (x86_64); the shared server needs an OIDC identity provider and SQLite or Postgres.

Works with

  • GitHub
  • Slack
  • Linear
  • Notion
  • Stripe
  • Gmail
  • HubSpot
  • Xero
  • MCP servers
  • OpenAPI documents

Capabilities

  • MCP
  • Agent gateway
  • Tool calling
  • Agent permissions
  • Human in the loop
  • TypeScript
  • Self-hosted

Strengths and limits

Strengths

  • The code is Apache 2.0 and the vendor sets no cap on users, agents or volume; it says a self-run Coral sends nothing to it, so data can stay inside your own cloud.
  • Rules work per operation: a custom tool such as closeStaleTicket changes one field on tickets idle for 30 days, so security approves one action instead of a whole API.
  • Across 34 tasks on GitHub, Linear and Slack with Opus 5.5, the vendor reports custom tools cut tokens by 37%, cost by 31% and time by 29% (README, read 17 November 2026).
  • The vendor states on its homepage FAQ that Coral is ISO/IEC 27001:2022 certified and logs every approval; no certificate was published, so ask for it.

Limits

  • Coral Enterprise, the edition that holds single sign-on, user provisioning and the immutable audit log, is listed as coming soon in the README, so regulated teams cannot buy those controls yet.
  • A shared team server needs an OIDC identity provider, a TLS reverse proxy and SQLite or Postgres, which is more setup than a hosted gateway.
  • On the Show HN thread (16 November 2026, read 2026-11-17) the maker said agent apps handle MCP approval prompts inconsistently, so Coral returns a link to its approval page; teams expecting in-chat approvals everywhere should test their own agent app first.
  • A commenter on the same thread found the name easy to confuse with Google's Coral hardware platform, and the maker agreed a suffix word may help; searches for the name bring up many unrelated products.
  • The speed and cost figures come from the vendor's own benchmarks, including a 100-task blind test it ran on 15 October 2026, and no independent replication was found.

How Hokai rates it

  • Ease of use7.0 / 10
  • Features7.5 / 10
  • Value for money8.5 / 10
  • Support5.5 / 10

Coral alternatives

ToolPrice fromFree planRuns onRating
Coral This page--YesWeb · Mac · Windows3.6
ExecutorPick Coral if you want per-operation Allow, Ask or Block rules on a gateway you host; pick Executor if you want the agent's apps, schedules and webhooks hosted for you.$15/moYesWeb3.2
ComposioPick Composio if you want a managed catalogue of 1,500+ app integrations; pick Coral if tools must be written by agents and run on your own servers.$29/moYesWeb3.8
ClawvisorPick Clawvisor if you mainly need credentials vaulted and work approved by task; pick Coral if you also want reusable agent-written tools with per-operation rules.$120/moYesWeb3.5

Coral facts

Compliance
ISO/IEC 27001:2022
Works offline
No
Minimum skill level
Intermediate
Price band
Free
Training-data policy
Per the vendor FAQ, a self-run Coral sends the vendor no data; the local metadata, custom tools and run records stay with you.

Data and privacy

Apache License 2.0 for the open-source edition; the ee/ directory holds Enterprise Edition code under its own license

Questions about Coral

How much does Coral cost in 2026?

The open-source edition is free under the Apache 2.0 licence, with unlimited data sources, agents and queries, and you run it yourself with your own LLM keys. Enterprise is priced by quote and adds SAML SSO, SCIM, advanced RBAC and an immutable audit log, though the README lists it as coming soon. No per-seat or per-call price is published.

Is Coral free to use?

Yes. The open-source edition has no limits on users, agents or volume, and the desktop app lets you try it on a laptop before any server rollout. Your costs are the model keys your agent already uses and, for a shared server, the host, identity provider and database you run yourself.

Which agents can connect to Coral?

Any agent or app that supports MCP. The README shows claude mcp add for Claude Code and codex mcp add for Codex, and points to a guide for Cursor, VS Code and OpenCode. You copy your workspace's MCP URL from the Coral UI and paste it into the client.

How is Coral different from an MCP gateway?

A typical MCP gateway decides which tools an agent can see, so a tool such as update_record can change any record it allows. Coral adds rules per operation, human approval and custom tools with fixed arguments. The vendor's own tests compare it with Kong, Composio and Microsoft's gateway.

Where does my data go when I use Coral?

Coral calls your SaaS APIs and databases directly, so nothing is copied into a warehouse first. It keeps a small local store of metadata, custom tools and run records that you own, and the vendor says nothing is sent to it when you run Coral yourself. Only the results an agent asks for reach its model.

About Coral

Coral is an open-source, self-hosted gateway from Phoebe Technology Limited (the repository is withcoral/coral) that sits between AI agents and the systems they work on. The team says it began while building an AI site reliability engineering agent that needed broad permissions and many tokens, and started from scratch on every incident. The repository was created in April 2026, reached version 1.8.0 on 13 November 2026 and has about 5,000 GitHub stars. A Show HN post on 16 November 2026 collected 51 points.

Read the full background

Agents call tools by writing short TypeScript programs and sending them through one exec tool. Each program runs in a fresh V8 isolate with no network access, no credentials and no imports. Coral checks every tool call against workspace policy, adds the credentials, then forwards the call to the provider, and it can pause the run until a person approves. When a program works, the agent saves it as a private custom tool, and a workspace owner can publish it as a shared tool for everyone.

It fits teams that let agents act on real systems: site reliability engineers who allow a rollback of named services only, support teams whose agent issues refunds with defined escalation, security teams isolating devices within approved groups, and analysts who want a custom tool to aggregate warehouse, CRM and billing data before the agent sees it. Agents connect over MCP, including Codex, Cursor, GitHub Copilot, ChatGPT and Gemini. You can start on the desktop app for macOS, Windows or Linux, or run a shared server with Docker Compose or Kubernetes.

Some buyers should pick something else. Composio hosts a large catalogue of ready-made app connections, and Executor hosts the apps and schedules an agent writes, so neither asks you to run a server. Clawvisor approves agent work by task and vaults credentials. Kong and Microsoft also publish MCP gateways that the vendor benchmarks against, and neither is linked here. Teams that need SAML single sign-on, SCIM provisioning or an immutable audit log today cannot get them: Coral Enterprise is listed as coming soon. For the wider shelf, see AI gateways and best AI agent builders.

The 1.8.0 release let operators define secret stores for credentials, and the 1.6.0 release of 10 November let agents save and delete saved functions from inside a program. Coral 1.0 replaced its earlier SQL interface with TypeScript programs and starts from fresh state rather than converting what version 0.x stored.

Our call: choose Coral if your team can run a server and wants per-operation approvals on agent actions. Choose Composio or Executor if you would rather not run one, and wait if you need single sign-on or an audit log this quarter.

Sources and guides

More AI Tools on Hokai

  • CometAPICometAPI is a unified API gateway: one key and one OpenAI-compatible endpoint for 500+ text, image, video and audio models, billed about 20% below official provider rates.
  • OrthogonalUnified API gateway for AI agents: one key and one prepaid balance reach dozens of paid data and search APIs, with no subscription and no per-provider signup.
  • AIML APIOne OpenAI-compatible endpoint for hundreds of AI models and agentic tools, billed from a single prepaid balance. There is no free plan: you pay as you go from a minimum top-up, and the vendor says it adds zero markup.
  • APIMODELSOne API key for image, video, LLM and audio models, billed only on successful calls, with pay-as-you-go top-ups from $10 and no monthly fee.
  • TouchmarkAI inference forward market (YC S26) where buyers lock in future token capacity on models like GLM, Kimi and Qwen below list price, delivered through an OpenAI-compatible API.
  • LiteLLMOpen-source AI gateway and Python SDK that puts 100+ LLM providers behind one OpenAI-compatible API, with budgets and fallbacks. Free to self-host.