Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.
Pensieve: never lose the thread. A local MCP server and Mac app that links your files, repos, agent sessions, tickets and messages into one thread per task, for you and your AI coding agents.
A brain-inspired, portable context database for AI agents
Build interactive web apps with Python running directly in the browser.
Open-source MCP server for AI agents — index code repositories, research papers, and datasets. Runs fully local.
Easy MCP (Model Context Protocol) servers and AI agents, defined as YAML.
The In-VPC Context Lake for AI Agents 🤖 A modular, infrastructure-first knowledge layer for engineering teams. Automates semantic indexing of technical sources (GitHub, Jira, etc.) to provide agents with precise, objective context — no SaaS, no data egress, and no black-box reasoning. Built for Agentic workflows.
A knowledge base for AI coding agents. Curate and organize your sources through an intuitive web UI. Give your agents a library they can explore efficiently. Built around a discovery–synthesis loop inspired by how humans research.
Moved to ultracontext/ultracontext
✔️ Login project application with Python, React and JWT.
A structured, end-to-end learning environment for Context Engineering — the discipline of deciding what information a model sees at inference time, obtaining it, assembling it safely, observing the result, and improving the system with evidence.
A context engineering platform for AI-assisted software development.
Context on Git - High-density, token-optimized LLM context engine for hardware and software repositories
unofficial implementation of Meta(facebook) Ai paper "Scaling test time compute for agentic coding"
An API to pass data down in the sub-function inspired by React Context
Modular RAG library for Python. Swap any component — LLM, vectorstore, reranker — with one line in a YAML file. No code changes. Just config.
EGMA: Enhanced GitLab MCP API Server, comes with 143+ tools for AI-powered GitLab integration, MCP server that connects AI assistants to GitLab with intelligent context awareness, URL deduction, and specialized tools for projects, issues, MRs, pipelines, and repository operations. Works with Claude Desktop, Amazon Q, Cursor
miniurl is a web application that allows users to generate unique, short identifiers for long URLs.
Context engineering toolkit for AI agents. Externalize, select, compress and isolate context. Prevents context bloat. Local-first Python tool for Claude, Cursor and LangGraph.
To associate your repository with the context-api topic, visit your repo's landing page and select "manage topics."