|
tooldocstest.dev — validate tool quickstart examples offline
Local-only CLI that checks tool quickstart example arguments and runs two allowlisted data-only sandbox tools, emitting deterministic pass/fail/unknown evide...
|
84 % |
|
praetr_ · review. apply. ship. recover.
Praetr catches your new files as they land, lets you preview the change against your live project, ship it, and confirms it actually went live. The whole loo...
|
80 % |
|
HookShield — local control for AI coding sessions
A local-first git hook for reviewing what AI coding sessions share before anything leaves your machine.
|
80 % |
|
tydig
|
79 % |
|
The Colour of My Thoughts
The desk of my mind.
|
79 % |
|
Canopy — from outcome to working software
One local-first IDE with two ways to build: let Canopy plan, route and verify an outcome in Build mode, or take full control of the same project in Engineer...
|
79 % |
|
VELIN Bug Agent
VELIN reproduces bugs in Solana developer tools, proposes a patch, and shows you the test runs before and after. You review before anything is applied.
|
79 % |
|
devtul.fun — Free Developer Tools. Fast, Local, Private.
Free online developer tools: JSON Viewer, YAML Viewer, Markdown Viewer, Regex Tester, Diff Checker, UUID Generator, Cron Generator, JWT Decoder and Base64 En...
|
79 % |
|
gateprobe - approval replay & binding-drift evaluator
Test whether an approval can be reused or bypassed after the target changes. Deterministic, versioned evaluator for agent approval tokens: catches binding dr...
|
79 % |
|
retryfuse: safe retry and reconcile for uncertain writes
retryfuse is a free, deterministic command-line tool that decides whether a failed or timed-out call is safe to replay. A post-write timeout returns reconcil...
|
79 % |
|
Static Analysis in Your Coding Agent’s Loop | SlopCop
Static analysis deep enough for CI, fast enough for your coding agent to run on every edit, so problems are fixed before you push.
|
78 % |
|
milim — Local control plane for coding agents
Use your own models and subscriptions, keep one canonical coding-agent thread, review the diff, and ship with milim.
|
78 % |
|
Forge · Review AI-built prototypes like real product work.
Publish a frozen version of your AI-built prototype. Stakeholders open a link, type six digits and pin comments to the real screens, and every comment comes...
|
78 % |
|
Virtual Engineer — Turn assigned tickets into reviewed changes
Turn assigned tickets into reviewed changes with the tools and AI agents your team already uses, on your own infrastructure.
|
78 % |
|
ReleaseTwin — self-serve release-proof testing
Self-serve release-proof testing. Compose HTTP and UI journeys, run them from your own CI, and prove a fix works by running the same case known-bad and known...
|
78 % |
|
Just Dashboard: one dashboard for the server you run
A self-hosted dashboard for one Linux server. Metrics, Docker, deployments, databases, a real shell, files and git, behind one login on your private network.
|
78 % |
|
conediff — diff two recorded AI runs
conediff compares two recorded AI runs across a model or tool swap and reports the outcome, cost, and latency diff with a per-step timeline. Deterministic, l...
|
78 % |
|
tracegrab — see what your API actually did
MCP-native runtime debugger. 31 tools let an AI agent set breakpoints, drive a scenario, and read a diagnosis — exceptions, N+1 queries, silent state loss, m...
|
78 % |
|
QAClan — browser and API regression, run on your machine
QAClan captures your browser flow and the API calls it fires, then replays both as one suite — on your machine, the same way every time.
|
77 % |
|
Runcurve
|
77 % |
Detected social media networks