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.
Repository Index
107,098 visible repositories in the index
625–648 of 652 · Most stars
🌳 Connecting ChatGPT with the Internet
Open source harness evals: which agent harness does tasks the best, for the least cost?
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
- agent-skills
- calibration
- claude-code
- decision-model
TranslatedPi.NET is a .NET 10 port of Pi. Pi is a minimal, extensible Agent harness (a TypeScript monorepo of about 171,000 lines). This project ports its core libraries one by one to net10.0, so that the .NET ecosystem can use the same set of capabilities.
- agent
- agentic-ai
- dotnet
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
DeepSeek Harness Desktop 插件,让 AI Agent 用自然语言构建、检查和维护可编辑的 SideFX Houdini 工程,支持程序化建模、HDA、场景诊断与渲染。 | A DeepSeek Harness Desktop plugin that lets AI agents build, inspect, and maintain editable SideFX Houdini projects with natural language, including procedural modeling, HDAs, scene diagnostics, and rendering.
- dsh-plugin
- houdini
- ai-agent
Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant
- ai-chat
- artificial-intelligence
- candle
- chatbot
Public code release for the paper "The Surprising Effectiveness of Deleting Weights in LLM Post-Training"
GPT-2 small (124M) in hand-written AArch64 assembly. No libc calls. About 100 tokens/s on an M1.
Evolved DSH plugin harnesses for five agent benchmarks, with versioned artifacts, evolution curves and Life-Harness comparisons
- agent-benchmark
- dsh
- harness
- leaderboard
Local billing dashboard for DSH model calls: multi-platform provider/model breakdowns of calls, tokens and spend, peak/off-peak pricing, manual CSV price import with peak windows, official-bill reconciliation, and HTML/PDF/CSV export.
- billing
- deepseek-harness
- dsh
- dsh-plugin
Integrate with the latest language models, image generation, speech, and deep learning frameworks like ChatGPT, DALL·E, and Cohere using few java lines.
- openai
- gpt3
- dalle2
- image-generation
TranslatedA Chinese-language guide to digital subscriptions and AI tools, including subscription instructions, risk warnings, and an FAQ.
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
- bland
- dspy
- livekit
- llm
Claude Code Gateway for Kimi, GLM, DeepSeek, and OpenRouter
- claude-code
- claude-code-alternative
- claude-code-api
- claude-code-free
CancerFoundation: A single-cell RNA sequencing foundation model to decipher drug resistance in cancer
- cancer
- foundation-model
- single-cell
This is a german ELMo deep contextualized word representation. It is trained on a special German Wikipedia Text Corpus.
- bilm
- elmo
- tensorflow
- machine-learning
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
- agent-orchestration
- cli
- developer-tools
- llm-agents
A powerful and easy-to-use PHP SDK for the Mistral AI API, allowing seamless integration of advanced AI-powered features into your PHP projects.
- ai
- api
- api-client
- api-wrapper
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain
The EU & UK compliance plane for Google ADK.