AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
reticle
reticle logo

reticle

Active·★ 1.3k·NOASSERTION·Updated 2026-10-21
★ Essential★ Trending

Reticle addresses a specific gap: a coding agent changes code and reports success without ever opening the app. It adds a dev-only SDK to a web or desktop app and gives the agent MCP tools to look at the page, act on it, observe what happened and assert an outcome.

Because the SDK runs inside the app, a check can see the network request a click sent and its response, the state in stores such as zustand, Redux, TanStack Query or Pinia, console errors and the source line of each element. Every check ends in a verdict of yes, no or unknown, and only yes counts as a pass.

A verified journey can be saved as a flow and replayed later without a model, and `reticle gate` can fail a CI run when a change touches a saved flow's code without a new passing run. The README lists support for React, Next.js, Vue, Svelte and Angular on the web, and Electron and Tauri on the desktop; the driven browser is Chromium.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
Not detected by GitHub
Latest release
v3.7.0 · 2026-10-13
Last commit
2026-10-18
Contributors
89
Forks
208
Open issues and PRs
210
First published
2026-06-11
npm package
@reticlehq/server 3.7.0 · 1,603 downloads last week

Source: GitHub, npm and PyPI public APIs.

#agent-skill#agent-skills#agent-testing#agent-verification#ai-testing-tool#automated-testing#claude-code#claude-skills
$ Install
$ npm install -g @reticlehq/server && claude mcp add reticle -s user -- npx @reticlehq/server mcp
↗ Visit site★ GitHub
01

Features

01Verdicts of yes, no or unknown with the evidence and file:line attached
02Reads network responses, store state (zustand, Redux, TanStack Query, Pinia) and console errors
03Saved flows that replay deterministically without an AI model
04CI gate that fails changes touching a saved flow without a new passing run
05SDK excluded from production builds; bridge listens only on 127.0.0.1
02

Why choose it

+Returns an explicit verdict with the request, state change or console line that decided it, instead of a screenshot to interpret.
+Says unknown when it cannot decide, so an inconclusive check is never reported as a pass.
+Saved flows replay without an AI model and can gate CI, so later changes cannot quietly break a verified journey.
03

Trade-offs

!It needs an SDK added to your app, so it does not work on apps whose code you cannot change.
!The server and CLI are under FSL-1.1-ALv2 (source-available, Apache-2.0 after two years); only the SDK, adapters and core are Apache-2.0.
!Browser driving is limited to Chromium, plus Electron and Tauri webviews.
04

Maintenance check

ActiveChecked: 2026-10-18
Last commit
2026-10-18
Commits, last 90 days
100+
Releases, last 90 days
22
Latest release
v3.7.0 (2026-10-13)
Open issues
210
Recent issues with at least one comment
11/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 156, 428, 223, 237, 161, 204, 7, 51, 81, 72, 85, 7

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #130 A standing false-green gate against third-party apps we did not write21 comments · 2026-08-09
  • #691 Lease Chromium failures all report the same wrong cause, and there is no fallback12 comments · 2026-08-31
  • #1001 [agent] The predicate grammar is still learned by provoking parse errors, in four places the error text does not name8 comments · 2026-09-19
  • #818 install-gate (windows-latest): the SDK is in the page and never dials the bridge — intermittent, and can take all five scaffolds at once8 comments · 2026-09-06
  • #453 Standardise event-listener teardown on AbortController (consistency, not a leak)7 comments · 2026-08-22

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude Code
MCP
Verified via docs
Cursor
MCP
Verified via docs
Codex
MCP
Verified via docs
Windsurf
MCP
Verified via docs
06

Quick start

1
$ npm install -g @reticlehq/server
2
$ claude mcp add reticle -s user -- npx @reticlehq/server mcp
07

Use cases

↳Check that a coding agent's fix actually works in the running app
↳Catch silent failures such as a 500 response behind a success message
↳Guard key user journeys in CI with replayable flows
08

Alternatives

⚡Top VS:
VScoder_eval★154→VSrepo-forensics★194→VSPyWry★99→VSskillhub★5.3k→
coder_eval logo
coder_eval★ 154
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
VSCompare→
repo-forensics logo
repo-forensics★ 194
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
VSCompare→
PyWry logo
PyWry★ 99
PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.
VSCompare→
skillhub logo
skillhub★ 5.3k
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
VSCompare→
agents-best-practices logo
agents-best-practices★ 2.4k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
VSCompare→
bub logo
bub★ 1.7k
Bub it. Build it. A tiny agent runtime, composable with plugins.
VSCompare→
anatomy logo
anatomy★ 18.6k
An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
VSCompare→
totally-integrated-claude logo
totally-integrated-claude★ 71
A Claude Code plugin for Siemens TIA Portal engineering automation.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
reticlehq /
reticle
↗

Lets a coding agent drive your running app and return a pass, fail or cannot-tell verdict with the file:line to fix

1.3k208
Last commit1d ago
StatusActive
CategoryDev Tooling
Contributors89
Latest releasev3.7.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.