Results for “context”

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in y

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and se

MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash

Always-on context for AI agents: screen capture, OCR, voice, MCP server. Local-first, AGPL-3.0.

Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks,

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped

Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.

Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.

Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file pa

Your AI agent finds the right files. Every time. Code graph context engine with 24 MCP tools — 170+ languages, triple se

Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip i

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchest

SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-ma

Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via ho

Run AI agents fully autonomously on a filesystem directory — MCP servers and skills enabled, with zero human approvals o

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and

Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and plugin system for Claude

Demo of ADK (Agent Development Kit) as an MCP (Model Context Protocol) client for flight search capabilities.

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

Open-Source Intelligent Command Layer

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

A simple and performant Model Context Protocol framework for Python.

Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, epi

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Co

Long-term memory for AI-coded codebases. A git blame for AI agents — but for the why. MCP server that captures the agent

Action Control for autonomous agents. Check posture. Gate risky actions. Prove execution. Fits your existing agent stack

Comprehensive MCP server providing real-time framework documentation access for Claude Code with intelligent caching, mu

MCP server that lets Claude Code and other AI agents read large PDFs without hitting context limits. Chunked reading, hy

Model eXecution + Context Protocol: Enterprise-Grade Data-to-AI Infrastructure

Model Context Protocol server exposing Google Drive, Sheets, Docs, Gmail, Calendar, and Apps Script as MCP tools. Python

Ship RAG based LLM web apps in seconds.

Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP

Yandex Tracker MCP Server with OAuth2 support

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures

Extends Model Context Protocol (MCP) to local LLMs via Ollama, enabling Claude-like tool use (files, web, email, GitHub,

Vault-native, accountable memory for Claude Code and MCP clients. Markdown is the source of truth, no LLM on the Stop pa

Persistent semantic memory server for MCP - Give your AI long-term memory that survives across conversations. Lightweigh

LLM-agnostic tabletop RPG Game Master framework. Runs on OpenCode, LM Studio, or any LLM service. D&D 5e included as ref

Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.

A comprehensive async Python library for TickTick with MCP support.