#Context-management
Showing 60 of 62 repositories tagged #context-management, ranked by stars
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The Context Platform for your Data and AI Stack
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
Cross-session context for Claude Code. CLI + MCP server + /story skill that tracks tickets, issues, handovers, and roadmap in a .story/ directory.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
Not an Amazon-style catalog or marketplace. ctx is a recommendation layer: bring your org tools or use the shipped graph to load the right skills, agents, MCPs, and harnesses only for the current dev window, cutting token bills and local compute waste: 79,958-node LLM-wiki graph, 68,494 skills, 467 agents, 10,790 MCPs, 207 harnesses.
Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack，让 AI 团队各司其职、自主稳定迭代。
Working memory for Claude Code - persistent context and multi-instance coordination
Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning
Local-first AI conversation memory hub to capture, search, summarize, and export chats across major AI platforms. 本地优先的 AI 对话记忆与知识中台。
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
Surgical context engineering with a nice UI, Windows, Mac, Linux, BSD, anywhere where python & Qt run
The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic Swarm parallel workflows. Auto-proceed rules. Automation patterns. Beads + Agent Mail + 50 bash tools. Supervise 20+ agents from one UI.
The memory layer for AI-native development — giving AI persistent understanding of your software projects.
Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.
One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.
Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.
Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.
Open-source memory coprocessor for AI agents. Persistent recall, semantic search, crash-safe capture. No hooks required.
CTX - Context Runtime Engine for Coding Agents
A repository that provides a structured system for maintaining context and tracking changes in Cursor's AGENT mode conversations through template files, enabling better continuity and organization of AI interactions.
ContextLattice is the local-first control plane for long-horizon agent memory and coordination.
Local context manager for Claude Code and Codex with workstreams, transcript binding, and branching.
Language AI Engineering Lab, a place where you can deeply understand and build modern Language AI systems, from fundamentals to production.
Personal Context Manager for Claude Code. Your life in walnuts.
A discovery and compression tool for your Python codebase. Creates a knowledge graph for a LLM context window, efficiently outlining your project | Code structure visualization | LLM Context Window Efficiency | Static analysis for AI | Large Language Model tooling #LLM #AI #Python #CodeAnalysis #ContextWindow #DeveloperTools
Nemp - The memory plugin for Claude Code that remembers everything.
从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill
Local coding-agent orchestrator — DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.
Self improving agents through iterations
Persistent memory for AI coding agents. Local-first, cross-session context, global knowledge, and optional autonomous task execution.
Your CLAUDE.md stopped working at 200 lines. Generate scoped skill files from your import graph, auto-sync on every commit. Claude Code and Codex.
Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.
A local AI client with Git‑style tree context. Branch conversations, compress long chats, and visually assemble per‑request context to avoid LLM “long-chat degradation.
Self-hosted AI workspace built around context management. Works solo, scales to teams.
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
ctx: do you remember? — a single-binary, local-first, convergent memory system for humans and machines.
AI-powered lorebook engine for SillyTavern. It retrieves relevant lore from your Obsidian vault using keyword matching and AI search, then injects it into context automatically.
A lightweight tool to optimize your Javascript / Typescript project for LLM context windows by using a knowledge graph | AI code understanding | LLM context enhancement | Code structure visualization | Static analysis for AI | Large Language Model tooling #LLM #AI #JavaScript #TypeScript #CodeAnalysis #ContextWindow #DeveloperTools
Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.
A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.
Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.
A skill for Antigravity that delegates scoped work to Gemini CLI or Codex CLI worker agents — keeping the main context clean.
🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team collaboration. Free to use.
Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.
Convert long AI conversations into portable conversation state graphs for LLM handoffs.
Fully automated memory and context management for Claude Code using hooks - Zero friction, zero context loss
Smarter context for Claude Code — semantic rule injection that learns what you need
ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.
Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言
Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automatic context injection. 📦 npm install -g memctx
Unified MCP context intelligence platform — pip-installable CLI that absorbed 6 foundational repos. Context engineering for AI agents.
Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.
Utilities for managing agent memory, context windows, and task-focused state
A powerful CLI to orchestrate workspaces and dynamically inject specialized skills into AI coding agents.
A Claude Code skill that keeps your AI grounded across long sessions: named responses + a living TASK.md for clean context handoff between instances. Works with any markdown-reading AI (Cursor, Copilot, Codex).
Timeless principles and best practices for working with language models - tooling-agnostic, future-proof, and clear.