Repository Index

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

• fine-tuning
• llama
• llms
• gemma

FauxPilot - an open-source alternative to GitHub Copilot server

A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.

• cheat-sheet
• cli
• gpt-3
• openai

TranslatedWorkBuddy international and domestic multi-account reverse proxy gateway, supporting Codex / Claude Code / DSH and standard OpenAI clients.

• api-gateway
• claude-code
• codebuddy
• codex

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

• agents
• calibration
• classification
• decision-making

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

• ai-safety
• benchmark
• clinical-decision-support
• dataset

FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.

• accuracy-decline
• ai-safety
• audit-trail
• fact-checking

TranslatedSprix AI at 屿智同行 (Yuzhi Tongxing, "island wisdom traveling together") × 保研岛 (Baoyan Dao, "Baoyan Island") — an open-source benchmark for AI agents in Baoyan advising and application planning.

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

• agent-security
• ai-agents
• audit-log
• claude-code

Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.

• calibration
• cuda
• cuda-graphs
• decision-making

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.

• benchmark
• calibration
• decision-making
• evaluation

PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

• llm
• mcp
• ocr
• pdf

HTTP honeypot on autopilot

• canarytokens
• deception
• deception-technology
• honeypot