R_REDDYX.XYZ

Context Engineering: open-source projects on GitHub

84 repositories on Context Engineering, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

AI Agents 1319Claude Code 1595LLM 2094MCP 1601Developer Tools 620Cursor 358Codex 849Agent 547Agent Memory 98AI Agent 690Claude 978RAG 533Agentic AI 378Memory 133
Snailclimb/JavaGuide

Java Guide

A comprehensive guide for interview preparation: Java, backend, databases, distributed systems, and high load.

★ 155,571 · Java
headroomlabs-ai/headroom

LLM Input Compression

Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting token usage by 60‑95% without loss of quality.

★ 79,744 · Python
gsd-build/get-shit-done

Meta-Prompting for Claude

A lightweight yet powerful meta‑prompting and context‑engineering system for refining and generating specifications in Claude Code.

★ 61,590 · JavaScript
bojieli/ai-agent-book

Deep Understanding AI Agent

Open repository of the book 'Deep Understanding AI Agent': full text, compiled PDF, and code for each section.

★ 58,104 · Python
shanraisshan/claude-code-best-practice

Claude Code Practices

From vibe-coding to agent engineering — a guide to productive work with Claude Code, compiled by the community.

★ 52,343 · HTML
VectifyAI/PageIndex

Vectorless RAG Index

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

★ 32,176 · Python
google/elephant-goldfish-model

SPEC-DRIVEN DEVELOPMENT WITH LLMS

Open-source method from Google for spec-driven development with LLMs. Skill set and plugins for Claude Code to formalize requirements into specs and generate code from th

★ 19,105 · Python
topoteretes/cognee

Memory for AI agents

Manage AI agent memory in just six lines of code. Simple integration with powerful capabilities.

★ 17,252 · Python
Canner/WrenAI

WrenAI Context Layer

The open context layer gives AI agents controllable SQL from 20+ sources, enabling GenBI, text-to-SQL, dashboards, and advanced analytics.

★ 15,184 · Rust
trailhq/Trail-Code

BOOST CLAUDE CODE

Boost Claude Code, Cursor, Codex, Gemini and other AI agents: faster, cheaper, with codebase‑aware context. It indexes your repo in seconds via tree‑sitter and delivers p

★ 11,274 · TypeScript
cocoindex-io/cocoindex

Cocoindex: Incremental Engine for Agents

An incremental engine for agents with long-term horizon. If you like it, give it a star!

★ 9,785 · Python
ai-boost/awesome-prompts

AWESOME PROMPTS: LLM ENGINEERING

Collection of 9141★ curated prompts, frameworks and papers for LLMs and agents with engineering bias. Covers prompt engineering, context engineering, agents and red teami

★ 9,245 · Python
plastic-labs/honcho

HONCHO: Memory for Agents

A Python memory library for building stateful AI agents, enabling storage and retrieval of context.

★ 4,592 · Python
foryourhealth111-pixel/Vibe-Skills

VIBE‑SKILLS: ENHANCE AGENT

Vibe‑Skills is an AI‑skill package with context management for instant upgrade of any agent.

★ 3,821 · Python
memodb-io/Acontext

ACONTEXT: MEMORY LAYER FOR AI AGENTS

Acontext creates a memory layer for AI agents, enabling skill persistence and reuse across sessions. The platform provides contextual storage, versioning, and agent execu

★ 3,695 · JavaScript
neomjs/neo

NEO: SELF-EVOLVING AI DEVELOPER

Neo.mjs is a self-replicating AI team that deploys a cross-model swarm into live applications via Neural Link, Hybrid GraphRAG, and self-healing cycles.

★ 3,199 · JavaScript
redhat-et/ripwire

RIPWIRE: CODE MAP FOR AI

ripwire — zero‑dependency C++23 CLI + MCP server that in seconds builds a deterministic ranked map of repo code, computes blast radius and suggests the set of tests affec

★ 2,543 · C++
microsoft/apm

Agent Package Manager

Agent Package Manager — a tool for managing agent packages, simplifying installation, updating, and configuration of agent components.

★ 2,421 · Python
kayba-ai/agentic-context-engine

AGENTIC CONTEXT ENGINE

The platform enables agents to learn from experience and improve their responses. Now available as a hosting solution on kayba.ai.

★ 2,316 · Python
rohitg00/pro-workflow

CLAUDE CODE LEARNS AND GROWS

Self-learning memory for Claude Code: context engineering, parallel worktrees, agent commands, and 17 proven skills.

★ 2,242 · JavaScript
aoci-spec/aoci-code

MCP SERVER FOR CODE CONTEXT

aoci-code — local MCP server and CLI in Go. Indexes code and DB schemas into a unified repo map. Helps AI agents (Claude Code, Cursor, Codex) understand complex systems f

★ 1,918 · Go
cocoindex-io/cocoindex-code

COCOINDEX-CODE - INSTANT CODE SEARCH

cocoindex-code – a lightweight AST-based CLI code search that saves up to 70% of tokens and speeds up AI‑agent work.

★ 1,834 · Python
chopratejas/headroom

headroom — compression for LLM

Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting tokens by 60–95% while preserving answer quality. Library, proxy, and MCP server.

★ 1,828 · Python
open-gsd/gsd-core

GSD-CORE: Get Stuff Done

Getting Shit Done, the Aftermath — a JavaScript framework with 1,721 stars on GitHub. Automate the routine and focus on what matters.

★ 1,721 · JavaScript
yvgude/lean-ctx

Lean-ctx: OS Context for AI

Reduce token usage in Cursor, Claude Code, Copilot and other AI tools by 60–95% (up to 99% with caching). One Rust program with 49 tools, 10 read modes, and 90+ patterns.

★ 1,667 · Rust
puppyone-ai/puppyone

PUPPYONE - AI CONTEXT DRIVER

A platform for managing AI-agent contexts, allowing easy data connection and improving their responses.

★ 1,604 · TypeScript
LilMGenius/paperthin

PAPERTHIN: SKILLS FOR RECURSIVE RSI

OpenAI hackathon winner's project on recursive agent self-improvement. Unpacks NVIDIA's zero-touch proof into engineering practice. Ready skillset for autonomous coding a

★ 1,445 · JavaScript
puppyone-ai/puppyone-cloud

CONTEXT MEMORY FOR AI AGENTS

Puppyone-cloud is a context engine for AI agents. It provides persistent storage, versioning, and instant retrieval of relevant context for LLMs. Simplifies building agen

★ 1,299 · Python
atomicstrata/llm-wiki-compiler

LLM AUTOMATICALLY COLLECTS WIKI

Knowledge compiler: raw sources → interlinked wiki. Inspired by Karpathy's LLM Wiki pattern; TypeScript, ⭐1292.

★ 1,292 · TypeScript
Houseofmvps/codesight

CodeSight: AI Context

Universal context generator for AI assistants. Saves thousands of tokens in Claude Code, Cursor, Copilot, and others.

★ 1,059 · TypeScript
DeepMyst/Mysti

AI Assistant for Code

Collaboration between Claude Code and OpenAI Codex in VS Code: joint brainstorming, discussion, and synthesis of the optimal solution.

★ 1,045 · TypeScript
melandlabs/openloomi

OPENLOOMI: YOUR AI WORK MATE

Openloomi is an open AI assistant that remembers all details of your work and offers helpful hints in real time.

★ 1,043 · TypeScript
alexgreensh/token-optimizer

Token Optimizer

Identifies and removes redundant tokens. Improves context quality during compression and prevents data degradation.

★ 1,034 · Python
Harvil1/codeAgent

CODEAGENT: AI AGENT FOR TERMINAL

CodeAgent — open-source AI agent working in the terminal. It analyzes the repo, plans changes, edits files, runs tests and repeats the loop until the task is done.

★ 1,012 · Python
ai-boost/awesome-harness-engineering

Awesome Harness Engineering

A collection of tools and patterns for AI agent engineering: memory, MCP, permissions, observability, and orchestration.

★ 941 · Python
promptise-com/Foundry

FOUNDRY: AGENT FOUNDATION

Foundry — base layer for creating intelligent agents in Python. Allows quickly building agent‑oriented systems.

★ 897 · Python
riponcm/projectmem

PROJECTMEM AI Agent Memory

Local memory for AI agents: records issues, attempts, and solutions, warning against repeating failed approaches. 100% local, with no cloud or telemetry.

★ 882 · Python
guanyang/open-agent-hub

LIGHTWEIGHT CLI FOR AI ASSISTANTS

Manage AI-assistant capabilities without dependencies. Support for Claude Code, Cursor, Trae and others.

★ 874 · TypeScript
shanraisshan/codex-cli-best-practice

FROM VIBE TO AGENT ENGINEERING

The project demonstrates best practices for using Codex CLI to transition from vibe coding to agent engineering.

★ 837 · Python
guanyang/antigravity-skills

FLEXIBLE SKILLS FOR AGENTS

Modular skills turn AI agents into full-stack, logic, and multimedia experts, enabling them to solve complex tasks step by step.

★ 836 · TypeScript
openmemind/memind

OpenMemind: Cognitive Memory AI Agents

Self-learning cognitive memory and context engine in Java for 24/7 active AI agents with understanding and SOTA performance.

★ 784 · Java
chenxiachan/thoughtdag

THOUGHTDAG Mind Map Online

Infinite canvas for LLM dialogues: turn conversations into an editable thought graph, where connections are context.

★ 783 · TypeScript
cortexkit/magic-context

MAGIC-CONTEXT - LIMITLESS CONTEXT

The project provides cache‑aware infinite context, inter‑session memory, and background history compression for LLMs.

★ 780 · TypeScript
mindmuxai/brain.md

BRAIN.MD – AI MEMORY FOR CODE

File memory for AI agents: stores decisions, requirements, and constraints without dependencies.

★ 711 · JavaScript
Tura-AI/tura

ACCELERATING CODE REFACTORING

Tura reduces the number of code rewrite steps by 83.1% and increases DeepSWE pass rate by 16.7 percentage points compared to Codex CLI.

★ 667 · Rust
qybaihe/mu

MU: SMART AGENT FOR CODING

mu (μ) — coding agent, which first evaluates the task with a small fast judge, then passes the complex work to the large model. Built on Pi and AionUi, written in TypeScr

★ 604 · TypeScript
Graphicle-AI/graphicle

CODE GRAPH FOR AGENTS.

graphicle — a single Rust program that builds a code graph and provides memory for the AI agents. Supports Claude Code, Codex, Cursor and any MCP clients, indexing the re

★ 571 · Rust
hoangnb24/repository-harness

REPOSITORY-HARNESS: REPO FOR AGENTS

Turns any repository into a workspace for Claude Code, Codex, Cursor and other AI agents. 559 ⭐

★ 559 · Rust
jfrog/boost

BOOST MAKE AGENTS SMARTER

A minimalist tool for speeding up and improving AI‑agent work.

★ 550 · Shell
nossa-y/activity-frames

EPISODIC AGENT MEMORY

Records the screen locally, builds structured activity frames, and serves them via MCP — without cloud or LLM in the chain.

★ 532 · Python
ultracontext/ultracontext

ULTRACONTEXT FOR AI AGENTS

Ultracontext — open source context infrastructure for AI agents. Automatically captures and shares agent context everywhere.

★ 442 · JavaScript
atomicstrata/atomicmemory

PORTABLE MEMORY FOR AGENTS

Portable semantic memory for AI agents: core, TS‑SDK, framework adapters, MCP server, CLI, and plugins.

★ 440 · TypeScript
laminlabs/lamindb

LAMINDB: AI DATA MANAGEMENT

Open platform for managing multimodal AI data: lineage-native data lake, support for biological formats from the creators of Scanpy.

★ 437 · Python
gotalab/skillport

Skills for Any AI Agent

Skillport allows managing AI agent skills via CLI or MCP. Configure once — use everywhere.

★ 422 · Python
ChristopherKahler/base

BASE: AI OPERATING SYSTEM

BASE turns Claude Code from a one-shot tool into a workspace that remembers context, self-maintains, and never gets stale. This is Builder's Automated State Engine in Rus

★ 388 · Rust
JamesShi96/project-butler

ASSISTANT MEMORY

Memory system for AI assistants: session logs, wiki, rules, TODO, and context handoff.

★ 377
fajarhide/contexere

CONTEXERE: CONTEXT LAYER FOR AI

Contexere (formerly OMNI) — context layer for AI coding agents. Compresses context by removing noise and saving tokens without information loss. Written in Rust, works vi

★ 377 · Rust
jahala/tilth

SMART CODE READING FOR AI

tilth finds definitions, callers, and function dependencies via tree-sitter. Works without indexing — single binary for CLI and MCP server. Install: cargo install tilth o

★ 362 · Rust
qf-studio/navigator

NAVIGATOR: CONTEXT FOR CLAUDE CODE

Navigator extends Claude Code sessions to 20+ exchanges, preventing crashes during long dialogues. It implements incremental context storage and a simple plug‑in integrat

★ 356 · Python
automagik-si/genie

GENIE: CLI AGENT FOR PRS

Genie is a CLI agent that interviews you, plans work, launches parallel agents in isolated worktrees, and reviews code before you see it. Just describe the task — get a r

★ 353 · TypeScript

New projects on this topic in Telegram

Telegram →
Context Engineering — 84 open-source GitHub projects | REDDYX AI