Change the repository type filter
All
Repositories list
39 repositories
open-associate-skills
PublicSkills bundle for simulating a top‑decile VC associate: market mapping, sourcing, diligence, memos, and portfolio ops.max
Publicdspy-micro-agent
Publicpetri-tribunal
Publictokio-hotel
PublicEphemeral, cancellable task rooms with scoped resources for Tokio runtimeskeep
Publicnimbus
PublicSelf-hosted CI infrastructure optimized for AI evaluation workloads. Run evals on bare metal with Firecracker isolation, built-in observability, and zero cloud …cursor-triplane
Publicagent-pm
PublicAgent PM: OpenAI Agents-powered product management orchestrator with automated PRDs, tickets, and comms.provenance
Publicmeta-secdev-agent
Publicgithub-ona
Publicenv-drift-detector
PublicDetect environment variable drift across monorepo services using OpenAI Codex SDK - catches naming inconsistencies, missing vars, and undocumented secretstenant-isolation-guard
PublicDetect missing tenant isolation in multi-tenant FastAPI apps using Codex SDK - prevents cross-tenant data leaks by catching missing workspace filtersgrimoire
Publictinker-eval-loop
PublicEvaluation-driven LoRA fine-tuning loop using Tinker API - automatically improve models through iterative training and evaluation cyclesstack
Publicmocktopus
Public🐙 Multi-armed mocks for LLM apps - Drop-in replacement for OpenAI/Anthropic APIs for deterministic testingmetaethical_breach_dspy
PublicDSPy implementation for detecting metaethical breaches in AI systems through systematic evaluation of moral reasoning patterns- DSPy + Lean (mock) iterative prover with hint clipping; sweeps on clipping vs KL, noise, sparsity; scalable dataset generator; curated training; frozen tools.
EvalATS
Publicoverride-cascade-dspy
PublicDSPy framework for detecting and preventing safety override cascades in LLM systems. Research-grade implementation for studying when completion urgency override…founder-email-optimizer
Publicllmcc
PublicLLM-native compiler toolchain - implementing 'LLM ≈ probabilistic compiler' with real OpenAI integration, structured outputs, and constrained decodingcongress-bill-search
PublicHigh-quality congressional bill search with hybrid BM25+vector similarity using DuckDB, TEI embeddings, and GovInfo API. Local deployment with Docker.orbit-agent
Publicfolie-a-deux-dspy
Publicproofcite
PublicCite or shut up. LLM answers without verifiable sources are liabilities. Extractive RAG with line-anchored citations that fails closed when confidence is low. D…eval2otel
PublicLibrary to convert AI evaluation results to OpenTelemetry GenAI semantic conventions for observability and monitoring