Git Stars Git Stars

#context-engineering Repositories

97
Total Repositories
1.1M
Total Stars
11,420
Avg Stars/Repo
51
Picrew/awesome-agent-harness

An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.

Picrew
โญ 1,969 Python ๐Ÿ‘ค Picrew User ๐Ÿ• Updated 2026-11-04 ๐Ÿ“… Created 2026-03-30
52
bubbuild/bub

Bub it. Build it. A tiny agent runtime, composable with plugins.

bubbuild
โญ 1,704 Python ๐Ÿ‘ค bubbuild Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-07-13
53
LilMGenius/paperthin

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.

LilMGenius
โญ 1,469 JavaScript ๐Ÿ‘ค LilMGenius User ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2026-06-19
54
Houseofmvps/codesight

Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.

Houseofmvps
โญ 1,425 TypeScript ๐Ÿ‘ค Houseofmvps User ๐Ÿ• Updated 2026-07-27 ๐Ÿ“… Created 2026-04-04
55
open-gsd/gsd-pi

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

open-gsd
โญ 1,380 TypeScript ๐Ÿ‘ค open-gsd Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-05-22
56
2akouwu/reverify

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.

2akouwu
โญ 1,350 Python ๐Ÿ‘ค 2akouwu User ๐Ÿ• Updated 2026-11-01 ๐Ÿ“… Created 2026-08-31
57
apecloud/ApeRAG

ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

apecloud
โญ 1,317 Python ๐Ÿ‘ค apecloud Organization ๐Ÿ• Updated 2026-10-29 ๐Ÿ“… Created 2023-06-20
58
puppyone-ai/puppyone-cloud

The cloud infrastructure behind puppyone. Hosts projects as Git repositories for your team and agents.

puppyone-ai
โญ 1,301 Python ๐Ÿ‘ค puppyone-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-12-06
59
hoangnb24/repository-harness

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

hoangnb24
โญ 1,271 Rust ๐Ÿ‘ค hoangnb24 User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-05-05
60
DeepMyst/Mysti

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.

DeepMyst
โญ 1,159 TypeScript ๐Ÿ‘ค DeepMyst Organization ๐Ÿ• Updated 2026-11-10 ๐Ÿ“… Created 2025-11-29
61
melandlabs/openloomi

OpenLoomi is an open-source AI coworker. It connects your work tools, understands what youโ€™re working on, and tells you what needs your attention, why it matters, and what to do next. Itโ€™s your open-source Attention Agent.

melandlabs
โญ 1,043 TypeScript ๐Ÿ‘ค melandlabs Organization ๐Ÿ• Updated 2026-09-24 ๐Ÿ“… Created 2026-04-10
62
shanraisshan/codex-cli-best-practice

from vibe coding to agentic engineering - practice makes codex perfect

shanraisshan
โญ 1,027 Python ๐Ÿ‘ค shanraisshan User ๐Ÿ• Updated 2026-06-04 ๐Ÿ“… Created 2026-02-27
63
Harvil1/codeAgent

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.

Harvil1
โญ 1,012 Python ๐Ÿ‘ค Harvil1 User ๐Ÿ• Updated 2026-10-14 ๐Ÿ“… Created 2026-10-02
64
guanyang/open-agent-hub

A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).

guanyang
โญ 1,007 TypeScript ๐Ÿ‘ค guanyang User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-01-13
65
repoprompt/repoprompt-ce

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

repoprompt
โญ 997 Swift ๐Ÿ‘ค repoprompt Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-05-12
โญ 952 Python ๐Ÿ‘ค sagar-n User ๐Ÿ• Updated 2025-11-10 ๐Ÿ“… Created 2025-08-13
67
openmemind/memind

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

openmemind
โญ 906 Java ๐Ÿ‘ค openmemind Organization ๐Ÿ• Updated 2026-08-13 ๐Ÿ“… Created 2026-03-19
68
promptise-com/Foundry

The foundation layer for agentic intelligence.

promptise-com
โญ 896 Python ๐Ÿ‘ค promptise-com Organization ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-08-29
69
AgnosticUI/agnosticui

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.

AgnosticUI
โญ 832 TypeScript ๐Ÿ‘ค AgnosticUI Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2020-09-07
70
chipfighter/context-attachment-manager

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.

chipfighter
โญ 812 TypeScript ๐Ÿ‘ค chipfighter User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-09-24
71
context-space/context-space

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

context-space
โญ 812 Go ๐Ÿ‘ค context-space Organization ๐Ÿ• Updated 2025-10-22 ๐Ÿ“… Created 2025-07-08
72
chenxiachan/thoughtdag

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

chenxiachan
โญ 799 TypeScript ๐Ÿ‘ค chenxiachan User ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2026-02-17
73
Snailclimb/AIGuide

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.

Snailclimb
โญ 752 ๐Ÿ‘ค Snailclimb User ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-04-15
74
mindmuxai/brain.md

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.

mindmuxai
โญ 721 JavaScript ๐Ÿ‘ค mindmuxai Organization ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2026-06-18
75
angel291592/Intent-Router

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

angel291592
โญ 718 Python ๐Ÿ‘ค angel291592 User ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2026-09-22
76
skillmatic-ai/awesome-agent-skills

The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture

skillmatic-ai
โญ 698 ๐Ÿ‘ค skillmatic-ai Organization ๐Ÿ• Updated 2026-05-14 ๐Ÿ“… Created 2025-12-22
77
agentic-os-org/ANOLISA

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

agentic-os-org
โญ 686 Rust ๐Ÿ‘ค agentic-os-org Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-30
78
Tura-AI/tura

Build agent that uses 80% less token and delivers better results.

Tura-AI
โญ 670 Rust ๐Ÿ‘ค Tura-AI Organization ๐Ÿ• Updated 2026-10-07 ๐Ÿ“… Created 2026-07-06
79
KirtiRamchandani/memory.cpp

Your repo remembers: local-first AI memory and context control plane for developers and coding agents.

KirtiRamchandani
โญ 661 Rust ๐Ÿ‘ค KirtiRamchandani User ๐Ÿ• Updated 2026-11-02 ๐Ÿ“… Created 2026-05-18
80
nadimtuhin/claude-token-optimizer

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.

nadimtuhin
โญ 661 JavaScript ๐Ÿ‘ค nadimtuhin User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2025-11-10
81
nicepkg/ctxport

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.

nicepkg
โญ 654 TypeScript ๐Ÿ‘ค nicepkg Organization ๐Ÿ• Updated 2026-03-04 ๐Ÿ“… Created 2026-02-07
82
winstonkoh87/Athena-Public

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.

winstonkoh87
โญ 649 Python ๐Ÿ‘ค winstonkoh87 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-12-18
83
Cluster444/agentic

An agentic workflow tool that provides context engineering support for opencode

Cluster444
โญ 636 TypeScript ๐Ÿ‘ค Cluster444 User ๐Ÿ• Updated 2025-09-02 ๐Ÿ“… Created 2025-08-12
84
qybaihe/mu

mu (ฮผ): most of what a coding agent decides isnโ€™t 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.

qybaihe
โญ 615 TypeScript ๐Ÿ‘ค qybaihe User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-09-22
85
Graphicle-AI/graphicle

Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.

Graphicle-AI
โญ 610 Rust ๐Ÿ‘ค Graphicle-AI Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-14
86
ooples/token-optimizer-mcp

91.5% fewer tokens in tool output on Headroomโ€™s 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.

ooples
โญ 590 JavaScript ๐Ÿ‘ค ooples User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2025-10-11
87
harish-gaggar/mcp-server-gateway

MCP gateway & OAuth MCP servers. LangGraph agent: memory, evaluation/tracking, PII protection, context trimming. Docker quick start for enterprise agents.

harish-gaggar
โญ 588 Python ๐Ÿ‘ค harish-gaggar User ๐Ÿ• Updated 2026-10-03 ๐Ÿ“… Created 2026-08-17
88
shanraisshan/claude-code-hooks

claude code hooks - adding voice on each hook

shanraisshan
โญ 572 HTML ๐Ÿ‘ค shanraisshan User ๐Ÿ• Updated 2026-06-04 ๐Ÿ“… Created 2025-11-05
89
ai-driven-dev/framework

Marketplace Framework AI-Driven Dev: Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC

ai-driven-dev
โญ 571 TypeScript ๐Ÿ‘ค ai-driven-dev Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-06
90
ratel-ai/ratel

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.

ratel-ai
โญ 566 TypeScript ๐Ÿ‘ค ratel-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-11-12
91
jfrog/boost

Save tokens. Maximize context, Safely

jfrog
โญ 554 Shell ๐Ÿ‘ค jfrog Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-03-02
92
adongwanai/learn-workbuddy

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

adongwanai
โญ 547 Python ๐Ÿ‘ค adongwanai User ๐Ÿ• Updated 2026-10-28 ๐Ÿ“… Created 2026-07-08
93
chandra447/pi-hermes-memory

Hermes-style persistent memory and learning loop for Pi coding agent

chandra447
โญ 535 TypeScript ๐Ÿ‘ค chandra447 User ๐Ÿ• Updated 2026-11-10 ๐Ÿ“… Created 2026-04-23
โญ 532 Jupyter Notebook ๐Ÿ‘ค langchain-ai Organization ๐Ÿ• Updated 2025-07-25 ๐Ÿ“… Created 2025-07-17
95
nossa-y/activity-frames

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

nossa-y
โญ 531 Python ๐Ÿ‘ค nossa-y User ๐Ÿ• Updated 2026-08-26 ๐Ÿ“… Created 2026-07-04
96
vanzan01/claude-code-sub-agent-collective

๐Ÿง  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.

vanzan01
โญ 526 JavaScript ๐Ÿ‘ค vanzan01 User ๐Ÿ• Updated 2026-04-20 ๐Ÿ“… Created 2025-06-06
97
nexi-lab/nexus

Nexus, the shared heartbeat where every agent and human connect, collaborate, and evolve together.

nexi-lab
โญ 516 Python ๐Ÿ‘ค nexi-lab Organization ๐Ÿ• Updated 2026-04-08 ๐Ÿ“… Created 2025-10-08