Crowded
Built with python
2050 projects in the corpus already ship on it. Expect company.
Reviewed ideas using python (25 of 28)
- BOB Forge — openLocal Codex diagnoses the incident. BOB Forge isolates and tests the patch, binds phone approval to the exact bytes, deploys, verifies, and rolls back locally.
- ClassLens — openDiagnoses what an Algebra-1 class misunderstands from their wrong answers, then builds a recheck quiz that verifies the fix. 41.1% @1 measured on 716 held-out real student answers.
- DeceptiForge — openDeceptiForge creates context-aware decoys across secrets, data, documents, and AI workflows—turning interactions into sensors that detect attacks, insider risk, and accidental AI leakage.
- LARS — Laboratory Analysis and Risk System — openVoice-activated AI assistant for food safety labs. Ask any question about pesticide residue data in natural speech — LARS answers instantly using Google Gemini Live API and real laboratory results.
- Deep Dive Skill — openAn adversarially-verified deep-research CLI skill that runs on 15 different AI coding agents — including Codex — and refuses to trust any claim until independent verifier agents fail to refute it.
- Imprint — openImprint turns any repository into a reusable Project Brain that can support Codex, Claude Code, and other coding operators without locking project context to one model or cloud.
- NOETHER — The Curiosity Engine — openLearn why AI hallucinates and how measurement catches it. Playable physics with computed black holes, a real broken benchmark, and GPT-5.6 as the map-maker, never the referee.
- FlakeFix — openA self-verifying agent for flaky tests: detects, diagnoses, fixes, and reruns until proven — then opens the PR. It never says fixed until it's watched the fix pass twice.
- Foresight — openPredicts the right GPT-5.6 tier for your task before it runs, then watches your Codex session live and kills it if it goes rogue on cost, scope, or secrets.
- Yatra — openHistorically-grounded AI walkthroughs - RAG-backed, not hallucinated. Pick any place and era, get a narrated journey through daily life there, with generated scenes.
- Sphere (Orbis) — openAI can lead a beginner to a solution, but it can't make them understand. Sphere can. It shows you, visibly, where your machine is broken and how to fix it, so you learn instead of just copy-pasting.
- Timeless Harness — openAn evidence-led governor that tests reusable Agent workflows against a native baseline and returns a provisional keep, narrow, revise, retire, or unresolved decision.
- LitMatrix - Evidence-Aware Research Intelligence Platform — openEducation: LitMatrix maps research evidence, reveals corpus-level blind spots, and helps students and professors test stronger research directions with traceable evidence.
- Firewall Guardian:The Autonomous Anomaly Detection — openAn intelligent AI agent that acts as a self-healing shield for network perimeters, autonomously detecting misconfigurations and malicious patterns in firewalls .
- JobAuto Studio — openA candidate-controlled Codex app that finds jobs, analyzes ATS fit, tailors verified one-page applications, and prepares submission in authenticated Chrome.
- MortalOS: Evidence That Software Can Die — openCreate once. Continue elsewhere—cryptographically verified digital life across browser loss.
- PhantomGuard - Anti-Hallucination Git Hook — openPhantom Dependency Guard scans AI-generated imports, verifies packages on npm/PyPI, and blocks commits containing phantom dependencies reducing supply-chain and dependency-confusion risks.
- Geometric Linguistic Transformations — openDiscover and test reusable geometric directions for negation, tense, questions, and other linguistic transformations inside transformer embedding spaces.
- TinyGPT — openSo this is a basic chat system that generates next token when you give it an input The best thing is that it is manually coded and made within 3 days
- Crest Invoice — openCrest Invoice helps sole proprietors and freelancers create, send, and track invoices in a delightfully easy way, free of charge.
- AgentsBoard — openAgentsBoard is a widget first iOS App with companion mcp/rest server, which let's your Agents keep you informed in non-invasive way by placing graphical actionable cards on you phone home screen.
- Foxy Audit — openStop promising your AI is safe. Start proving it with cryptographic proof, not just your word.
- Oysterun AgentStore — openClone agent with one click. Even your mom can run agent.
- Genesis — contestedGenesis is autonomous AI organization, transforms single sentence into deployed SaaS product.It consists of specialized AI employees that collaborate, debate, evaluate and execute like a real startup.
- Canary — openCanary is an autonomous AI agent that red-teams other AI systems for prompt injection — live, in a real browser — and only reports a finding once the target itself proves it.