Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
- claude-code
- token-optimization
- context-window
- token-usage
61,275 visible repositories in the index
217–240 of 342 · Most stars
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
TranslatedUnified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. A research workspace for collaboration between humans and agents; fills the human-machine context gap of the Zotero era.
Manages Unified Access to Generative AI Services built on Envoy Gateway
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
UNIGIT public brand and ecosystem hub — AI should work for everyone.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
On device Firewall for Coding and Personal Agents
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
Messaging APIs for multi-platform
🦎 A lightweight, streaming-native, multi-protocol gateway for AI, APIs, and real-time data. Route LLM requests across providers, govern MCP tools, and connect Kafka, MQTT, and HTTP through one high-performance engine with shared security and observability.
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
Newelle - Your Ultimate Virtual Assistant
💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI, Ollama, Anthropic, ..]