|
Trust what your AI writes - a deterministic check · doloop
AI writes your code and pulls your data - but can you trust it? doloop flags what it can prove, deterministically, the same verdict every run. Bring your own...
|
83 % |
|
Forge — AI agents that just work
AI that just works. Hundreds of AI teammates doing real work around the clock — planning, building, reviewing and finishing it.
|
83 % |
|
dot•requirements
Readable, testable, AI-native requirements that live alongside your code.
|
83 % |
|
Excellent — Verification for agentic tasks
Excellent runs next to your AI agents, checks their work with independent evidence, and tests changes that make them more reliable on your own work.
|
82 % |
|
Corvid. The programming language that checks your AI before it runs.
Corvid is the first programming language designed for the age of AI. Dangerous AI actions either compile with a proof or do not compile at all.
|
82 % |
|
YesAI — Tested AI Strategies, Prompts & Workflows
YesAI is a multilingual tested AI strategies, prompts, workflows, and evaluations library for creators, operators, indie builders, and AI power users.
|
82 % |
|
Reachability - Helping You Build More Responsive Agentic AI
Reachability runs continuous checks on your AI agents and app flows. Verify every GitHub PR is correct, testable, and human readable.
|
82 % |
|
Variance Authority — Understand the code. Investigate the behavior. Check the work.
Open-source tools for developers and coding agents: source intelligence, live test inspection, test selection and reduction, UI analysis, and change verifica...
|
82 % |
|
Good Vibes Only — Human Code Review for AI-Built Apps
|
82 % |
|
noSwag: Agentic Tests for AI-Built Apps
Agentic test generation for vibe-coded apps and AI-generated code dumps. noSwag turns messy code into reviewable pytest and Vitest files your team can own.
|
82 % |
|
Sarkar AI — Hello, World.
Sarkar AI builds tools for the age of AI agents — local execution with Deskmate, observability with Riva.
|
82 % |
|
devx-ai — LLM Evaluation & Observability
Evaluate, trace, and test your LLM applications.
|
82 % |
|
Ship & Tell — Launch your product to the right communities
|
82 % |
|
TheGitAI — Agentic AI Coding Tool for Your Terminal
TheGitAI is an agentic AI coding tool for your terminal. It investigates, edits, tests, and documents your code. No provider account or API keys, and every A...
|
82 % |
|
Home
Legible verifies workflow correctness in production, detecting silent regressions like missing steps, path drift, and deploy-induced changes, even when metri...
|
82 % |
|
Deslopus — Make Coding Agents Produce Less Slop
Deslopus is an open-source initiative to make AI coding agents write code that survives the next change.
|
82 % |
|
Frontal Codes — Ship software by describing it
Local-first, no-code AI agent orchestration. Describe your goal in plain language — Frontal plans it, dispatches coding agents to isolated git worktrees, val...
|
82 % |
|
PtcRunner
PtcRunner is a runtime for building self-improving agents: the agent loop is a replaceable library, not the runtime, so you can change what an agent does wit...
|
82 % |
|
alidoes.ai — run it, then check it
AI can sound completely sure and still be confidently wrong. I run my real life on AI agents and show the independent checks that catch what looks right but...
|
82 % |
|
Hammy Devy — an AI engineering agent that digs until it works
An AI engineering agent with durable memory, semantic code search, background work queues and real security controls. Managed hosting available — no install.
|
81 % |
Detected social media networks