Open source. Open possibilities.

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.

Minimal FastAPI proxy for OpenAI Chat Completions and Embeddings APIs. Supports multi-tenant key mapping, streaming, and official SDK compatibility without a database.

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.

A local, read‑only dashboard that visualizes Claude Code usage—token counts, cost estimates, sessions, tools, skills, projects, and activity patterns—by scanning ~/.claude/projects/ and serving a FastAPI‑based UI.

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.

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.

Provider-neutral FastAPI gateway for LLM routing, retries, fallbacks, structured output, and usage/cost accounting. Supports Gemini and OpenAI with model aliases, retry policies, and persistent usage tracking.

A large language model-based virtual world life simulator supporting multi-agent NPCs, hierarchical memory, causal evolution, and natural language narrative, capable of creating multiple world types and running autonomously.

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.

AI-powered real-time visual novel engine with streaming narrative, character sprites, scene backgrounds, branching choices, and co-creation. Runs as desktop app or browser via FastAPI+SSE.

LearnNote is a local-first AI learning assistant that transforms videos from Bilibili, YouTube, and local files, as well as PDFs, into structured notes via subtitles or transcription, supporting reading, editing, and exporting in a web workbench.

Defense-only fraud detection for cross-merchant identity reuse. Sentinel builds an identity link graph across merchants, scores payment events deterministically with explainable verdicts, and provides an analyst console, audit trail, and measured precision, recall, and false-positive cost in rupees.

SkyClass Distill is a pipeline tool that transforms teaching videos into structured Teaching Skills, supporting video collection, transcription, evidence extraction, and LLM distillation.

MyCut is an AI video editing Agent that provides a complete creative closed-loop, from trending topic selection and copywriting generation to automatic video slicing.

PASO is a production-grade, real-time communication platform featuring AI moderation, voice/video calling, and scalable Socket.IO infrastructure. It combines messaging, AI features, and administrative controls.

SYNAPSE is an AI-powered intelligence aggregation and automation platform featuring a multi-agent system and RAG capabilities for research and document generation.

A local facial recognition attendance system with a React Native Expo mobile app and FastAPI Python backend. It captures faces via Expo Camera, processes them with OpenCV LBPH, and logs timestamped attendance into SQLite.

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.

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