Open source. Open possibilities.

AetherGrid is a distributed AI workload orchestrator built with strict Domain-Driven Design, featuring lease-based execution ownership, event-driven reconciliation, API key auth, and a React dashboard.

FairMind is an open‑source AI governance platform providing bias detection, fairness testing, and compliance tracking for ML, LLM, and multimodal AI models. It offers evidence‑grade evaluation, model registry, and remediation tools.

A full-stack project template combining FastAPI, SQLModel, PostgreSQL, React, Vite, Tailwind CSS and shadcn/ui, with JWT auth, Docker Compose deployment, Traefik HTTPS, email recovery and CI/CD.

Peaky Peek is a local-first, open-source audit and trust console for AI agents. It captures causal chains, verifies claims deterministically, and produces explainable trust scores with failure narratives — all running on your machine.

Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, reducing token usage while preserving key information. Runs locally as a Python/TypeScript library, proxy, MCP server, or agent wrapper for Claude Code, Codex, Copilot, Cursor, and more.

Felix is a self-hostable agents harness that compiles YAML manifests into governed agents with durable execution, memory, skills, evaluation, approvals and sandboxes, exposed via REST/SSE, OpenAI-compatible, A2A and MCP APIs.

FastAPI is a modern Python web framework for building APIs with standard type hints, featuring automatic OpenAPI documentation, data validation via Pydantic, high performance via Starlette, and interactive Swagger UI and ReDoc interfaces.

PARTHA turns one repository revision into a sealed, queryable intelligence model — building architecture graphs, dependency graphs, engineering reviews, insights, documentation, and optional AI context from a single persistent snapshot with evidence and provenance.

PyCaret 4.0 is an open-source, self-hosted AutoML platform for Python: a sklearn-native engine plus a FastAPI control plane and React UI, runnable locally with a single docker compose command.

Hatchet is an open-source orchestration engine for background tasks, AI agents, and durable workflows. Supports Python, TypeScript, Go, and Ruby via self-hosting or Hatchet Cloud. Features task retries, cron jobs, DAGs, real-time monitoring, and multi-tenancy.

Self-hosted, MIT-licensed API for dispatching content to 7 social platforms via one HTTP call. Supports scheduling, retry, webhooks, AI caption adaptation, and media transcoding. Zero vendor lock-in.

A lightweight local API proxy that reduces LLM API costs by compressing chat history, removing redundant code, and implementing semantic caching.

Design Oracle analyzes a website with Playwright and extracts its design system—colors, typography, spacing, components and UX patterns—then exports Tailwind v4 config, React JSX, JSON design tokens or a DESIGN.md report. It runs standalone or as an MCP server for AI agents.

BGSTM is a methodology-agnostic software testing framework built on six core phases, from test planning to results reporting. It ships guidance, templates, worked examples, and a self-hostable FastAPI + React reference application with traceability and quality dashboards.

fastapi-faults is an MIT-licensed Python package for FastAPI that defines typed RFC 9457 Problem Details from domain exceptions, reuses one immutable Fault definition for runtime responses and OpenAPI documentation, and supports feature-local registries, typed extension fields, and built-in framework error normalization.

SQLModel is a library for interacting with SQL databases in Python, designed to reduce code duplication by combining SQLAlchemy and Pydantic.

WhisperLiveKit is a self-hosted, ultra-low-latency speech-to-text pipeline. It provides real-time transcription, speaker diarization, and translation via WebSocket and OpenAI/Deepgram-compatible APIs.

llm-apipool aggregates 40+ free LLM APIs into one OpenAI-compatible endpoint. Auto-rotates keys, handles rate limits, tracks usage, and supports CLI, TUI, proxy, and LangChain integration.

Self-hosted GitHub App that publishes a required check accepting human CODEOWNER approval or approval from explicitly enrolled GitHub Apps, with organization and repository policies; pre-release and shadow-mode only.

Recotem is a recipe-driven recommender system tool built on irspack. One YAML defines data, training, and output; train produces a signed artifact, serve mounts it as a REST API with hot-swap. Single binary, no database.