TranslatedBullFlow — Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. The entire knowledge base pipeline runs on local open-source models, with no paid models needed; AI Agent creates image-text posts / images / videos, with one-click publishing to 17 platforms including Douyin, Xiaohongshu, WeChat Official Accounts, LinkedIn, and YouTube. Commercial-grade, multi-tenant, billing & admin built in. MIT
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
Manage and use multiple Ollama instances with automatic offline detection/failover and model availability tracking
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
The E2E AI testing tool | No ML Overhead
- ai
- rag
- rag-evaluation
- rag-pipeline
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis
Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.
Package to set up autonomous agents to trade on TBD
Catch silent failures in agent workflows by verifying real system state