#99th of 19 in Code review and testing
reticle
MCP tools that let coding agents verify a running app and return pass, fail or unknown
- Stars
- 1.3k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
1 on 12 Jun 20261,267 on 23 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Reticle adds a dev-only SDK to your web or desktop app and exposes reticle_* MCP tools so a coding agent can click through the running app and read network responses, store state, console output and source lines. Each check returns a verdict of yes, no or unknown, with the evidence and a file:line to fix. Passing journeys can be saved as flows, replayed without a model, and enforced in CI with `reticle gate`.
Who it is for: Developers using MCP coding agents who want UI changes verified automatically
Ranked among open-source alternatives to CodeRabbit (#9 of 10).
Strengths
- Verdict includes the request, state change and console line behind it, plus a file:line
- Returns `unknown` when it cannot decide, so there is no silent pass
- Saved flows replay deterministically with no model; `reticle gate` checks them in CI
- Production builds exclude the SDK; bridge binds to 127.0.0.1 only
Weaknesses
- Server and CLI are FSL-1.1-ALv2 (source-available), not OSI open source until two years on
- `reticle init` edits build config, agent rules files, MCP config and prompt hooks
- Anonymous usage telemetry is on by default; opt out with an env var or command
- Harness and dashboard are on the hosted platform; full open-source scope is unclear
What it needs
- no GPU
- Needs Node 20.11+, Chromium browser, MCP-capable coding agent
- port 4400
Quick answers
Is reticle open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Also in Code review and testing
See all 19| Rank | Project | Score |
|---|---|---|
| 1 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 92 out of 100 |
| 2 | react-doctorCLI that scans React codebases for state, performance, security and accessibility issues | 90 out of 100 |
| 3 | pr-agentLLM pull request reviewer that comments via /review, /describe and /improve | 87 out of 100 |
| #4 | e2eAI-driven end-to-end testing framework for web and mobile apps | 86 out of 100 |
| #5 | hunkTerminal diff viewer for reviewing code changes, with inline agent notes | 85 out of 100 |