Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, reducing token usage while preserving key information. Runs locally as a Python/TypeScript library, proxy, MCP server, or agent wrapper for Claude Code, Codex, Copilot, Cursor, and more.
Open source. Open possibilities.
Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONRAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with Agent capabilities to provide a high-fidelity context layer for Large Language Models.
A curated library of machine-readable task prompts and Agent Skills for coding agents, focusing on common agent failures like broken setup scripts, vague issues, and tests requiring unavailable services. Includes fixtures with planted defects for validation.
MCP Context Server is a FastMCP-based server providing persistent multimodal context storage for LLM agents, featuring full-text, semantic, and hybrid search with cross-encoder reranking, thread-based scoping, and support for SQLite and PostgreSQL backends.
Semantica is a graph-native infrastructure designed to provide structured context, deterministic reasoning, and full decision provenance for AI systems, serving as a semantic layer for LLMs and agents.
Haystack is an open-source AI orchestration framework for building production-ready LLM applications, RAG systems, and autonomous agents in Python.
JavaGuide is a systematic knowledge base for Java backend developers and interviewees, covering Java fundamentals, collections, concurrency, JVM, databases, distributed systems, system design, and AI application development, while providing learning roadmaps and interview preparation advice.
UE5 asset workbench plugin enables scripts and AI agents to read, edit, import, migrate, and audit Unreal Engine 5 uasset files by exporting structured JSON and applying changes via commandlets, supporting Blueprints, animations, widgets, materials, Niagara, levels, etc.
PageIndex is a vectorless, reasoning-based RAG engine that builds hierarchical tree indexes for long documents and lets an LLM reason through the tree to retrieve relevant sections, avoiding vector databases and chunking.
AgnosticUI Local (v2) is a CLI-based, framework-agnostic UI component library that copies component source, styles and tests directly into your project for React, Vue, Svelte or Lit, with 55 accessible components, CSS custom-property theming and AI prompt playbooks.
TraceFrugal is a local Go application that visualizes token usage for Claude Code and Codex, offering MCP result packing, cost regression gates, and optimization trials to help developers manage AI context efficiency and verify savings.
RightMemory provides durable memory, a user-directed Pursuit map, and reusable Agent Corrections for AI coding agents. It stores context as Git-syncable Markdown trees organized in a graph with typed edges, enabling multi-device continuity and multi-agent collaboration while keeping memory ownership explicit and vendor-neutral.
OpenSpec is a spec-driven development framework that helps AI coding assistants plan and agree on requirements before writing code, using Markdown spec artifacts and slash commands.
GSD Core is a lightweight, spec-driven framework for AI coding agents that manages milestones through discuss, plan, execute, verify, and ship phases. It isolates heavy work in fresh-context subagents, preserves structured session artifacts, and supports multiple runtimes.
Curated guide to Claude Code best practices: subagents, commands, skills, workflows, hooks, MCP, memory, settings, plus newer features and an orchestration workflow pattern.
Agentic OS is a self-hosted control plane for running business operations as a fleet of AI agents. It features a cost-aware LLM router, cross-module workflows, and human-in-the-loop approvals for finance, support, and compliance.
Context Engineering Protocol provides AI coding-agent skills that assemble human-approved, source-attributed context packages — code graphs, requirements, org conventions, and constraints — before generation runs. It detects gaps, conflicts, and staleness across sources, gates output behind explicit human approval, and supports Claude Code, GitHub Copilot, Cursor, and OpenAI Codex.
CocoIndex is an open-source incremental indexing framework designed to provide AI agents and LLM applications with continuously fresh context by reprocessing only changed data.