#context-engineering Repositories
97 repositories total
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
Stop your AI from making things up โ it proposes, deterministic tools decide, and every claim is checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
The cloud infrastructure behind puppyone. Hosts projects as Git repositories for your team and agents.
Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.
OpenLoomi is an open-source AI coworker. It connects your work tools, understands what youโre working on, and tells you what needs your attention, why it matters, and what to do next. Itโs your open-source Attention Agent.
from vibe coding to agentic engineering - practice makes codex perfect
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done โ all with a transparent, extensible tool loop.
A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).
Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.
Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.
AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.
A local plugin for image-heavy chats in Codex, Claude Code, and other AI agents: earlier images are replaced with short placeholders instead of being sent with every message, the model retrieves the original by its ID (even after compaction), and the prompt cache keeps working.
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
AI application development, AI programming practice, and interview guide, covering core technologies and engineering practices such as LLM, Agent, RAG, MCP, Claude Code, and Codex.
A persistent, file-based memory layer for coding agents โ give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.
Intent compiler for AI agents โ converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
Your repo remembers: local-first AI memory and context control plane for developers and coding agents.
Cut the tokens Claude Code loads at session start. A CLI that sets up a small CLAUDE.md with on-demand docs, measures startup tokens, and keeps them small.
Copy AI conversations as clean Markdown Context Bundles โ one click from ChatGPT, Claude, Gemini, DeepSeek, Grok & GitHub. Copy from sidebar without opening. Zero upload, 100% local, open source.
Turn stateless LLMs into a stateful, compounding AI agent. Local-first persistent memory, quantitative decision screens, and governance harness across Claude Code, Antigravity, Cursor, and VS Code. Own the state. Rent the intelligence.
An agentic workflow tool that provides context engineering support for opencode
mu (ฮผ): most of what a coding agent decides isnโt code. mu hands 40 kinds of yes/no decisions to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.
91.5% fewer tokens in tool output on Headroomโs own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini, and 12 more. Local, MIT.
MCP gateway & OAuth MCP servers. LangGraph agent: memory, evaluation/tracking, PII protection, context trimming. Docker quick start for enterprise agents.
Marketplace Framework AI-Driven Dev: Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC
The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes, and runs evaluations on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDKs.
Recreate a WorkBuddy-style desktop AI assistant harness from scratch: a 24-chapter Python tutorial covering the Agent Loop, tool calling, memory systems, Sidecar, sandbox auditing, and DeepSeek/OpenAI evaluation traces
Turn your workday into structured workflows agents can execute. 100% local, served over MCP.
๐ง Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.
Nexus, the shared heartbeat where every agent and human connect, collaborate, and evolve together.