Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 28 of 41
Agent Brain CLI - Command-line interface for managing AI agent memory and knowledge retrieval
Persistent two-tier memory for AI agents. Short-term markdown + long-term SQLite with semantic search.
Type-guided externalized state for LLM agent frameworks.
Content-addressed artifact manifest for AI agents (Python port of @p-vbordei/agent-cid)
Version control for AI reasoning — every LLM turn gets a content-addressed, queryable commit ID
Portable system context for agents, checked into the repo.
Lightweight context window management for AI agents
A document-to-agent-context compiler.
Intelligent context management for AI agents with cost optimization
Agentic Context Engineering (ACE) middleware for LangChain — self-improving playbooks from the ICLR 2026 paper by Zhang et al.
Microsoft Agent Framework AstraDB.
Azure Cosmos DB for NoSQL integrations for Microsoft Agent Framework.
Microsoft Agent Framework CosmosDB.
Engram (Lumetra) durable memory tools and middleware for the Microsoft Agent Framework.
GoodMem integration for Microsoft Agent Framework.
Mem0 integration for Microsoft Agent Framework.
Microsoft Agent Framework Memory.
Redis integration for Microsoft Agent Framework.
Git for AI Memory. Prevent hallucinations with save points.
Session continuity toolkit for AI agents. Generate and maintain context handoff files across sessions.
AgentKnowledgeMCP - Advanced Knowledge Management for AI Agents
AgentKnowledgeMCP - Advanced Knowledge Management for AI Agents
Reusable self-learning engine for agent workflows
Persistent memory for AI agents doing literature review with your taste.
A command-line journal built for AI agents, with semantic search.
Memory Fast and Slow for AI Agents
一个完整的、智能的、多层次的Agent记忆管理系统
Python client for the Agent Memory Server REST API
Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX graph) for AI agents
Zero-config, traceable, MCP-native long-term memory for agents.
Enterprise-grade agent memory management solution with region governance.
A reusable memory layer for SAP agentic workflows
Lightweight memory store for AI agents — pure Python, zero dependencies
Persistent memory for AI agents — store, retrieve and search knowledge across sessions
A Memory Server for LLM Agents and Applications
Placeholder package — install mcp-memory-service instead.
Long-term memory management for AI agents
Hybrid retrieval memory for AI agents - BM25 + vectors + knowledge graph with RRF fusion
Structured session checkpointing for AI agents — survive context limits, cost overruns, and session death
Hierarchical memory management for AI agents with vector search and graph relationships
A simple decorator for tracking and reverting agent actions
Cross-session memory and analysis layer for the Rigged tool suite
Byte-deterministic transcript format for AI-agent conversations (Python port of @p-vbordei/agent-scroll)
Cross-session context persistence and resumption
Python backend utilities for sharing app state with AI agents. v1: {messages, actions, context} model, breaking changes, RAG-ready architecture.
Local-first MCP tools: workflow routing/spec + keyword memory (JSON) with optional toggles.
Rich threads for AI agents
Persistent virtual filesystem for AI agents, backed by SQLite or Postgres
Context compression middleware for AI agent frameworks — automatically summarizes conversation history when token limits are approached
Create an agent that can handle a large number of tools with persistence support.
Persistent memory and multi-agent communication — three transports (AgentTalk, Email, FTP), all open, all self-hostable
One brain for all your coding agents. Local-first memory that syncs across Claude Code, Codex, Cursor, and any MCP client.
Task Tracker, Memory and Orchestration System for AI agents.
Modern Agent Management & State Persistence Framework
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers. Python port of @mukundakatta/agentfit.
Real-time data platform serving context to AI agents
Postgres-backed ChatHistoryStore for AgentForge
Redis-backed ChatHistoryStore and SessionLock for AgentForge
Neo4j-backed MemoryStore and GraphStore for AgentForge
Postgres + pgvector-backed MemoryStore and VectorStore for AgentForge
SQLite-backed MemoryStore and VectorStore for AgentForge
SurrealDB-backed MemoryStore, VectorStore, and GraphStore for AgentForge
Portable binary graph memory for AI agents
Core component for Agent Memory and Task Management
Longitudinal user modeling for AI agents
Automatic context window management for AI agent SDKs
Agentic Context Engineering utilities for OpenAI Agents.
Store agent conversation logs (e.g. Claude Code JSONL) as HDF5 for cheaper context reconstruction, analytical queries, and self-contained provenance.
Production-Grade Agent Memory Framework for Agentic AI
Drop-in SDK to add an AI memory layer to any application. Works with OpenAI, Anthropic, Gemini, Claude.
A Graph-Theoretic Memory Kernel for Agentic AI Systems
Framework-agnostic memory layer for AI agents. Multi-signal retrieval, conflict detection, typed decay, checkpointing. Zero dependencies.
A BYOK Hierarchical Graph Memory library for AI agents.
One-command installer for the Agentic Memory Hermes Agent plugins
Existential grounding for AI agents
Temporal reasoning for AI agents
Persistent memory + multi-agent channel for any AI stack. The memory that never forgets.
A Python client for the AgenticMem API
Official Python SDK for Agentic Memory — 3-tier persistent memory for AI agents. Short-term recall, semantic search, and auto-summarised knowledge in one API.
Python SDK for Agentified — Context Intelligence Layer for AI agents
Transitional package for aiqtoolkit-mem0ai, this package is deprecated and will be removed in the future.
Transitional package for aiqtoolkit-zep-cloud, this package is deprecated and will be removed in the future.
Context and trust integrity for multi-agent and long-running AI agents.
Cognitive continuity infrastructure for long-lived AI agents — cross-model state reconstruction, semantic recall, cognitive compression
MongoDB Session Store extension for Agent Kernel
Official Python package for Agentknowledge.
The SQLite of agent memory — embeddable vector + graph store for AI agents
A recursive learning framework that gives any AI agent a self-improvement loop with memory
Persistent decision memory for any project. Karpathy's LLM Wiki, productized.
A mem0-compatible memory SDK powered by Alibaba Cloud AgentLoop (CMS)
Virtual filesystem for Alibaba Cloud CMS AgentLoop Memory API - Agent-friendly design
AgentLoop SDK — middleware that turns human corrections into searchable memory for your agent.
Drop-in Anthropic SDK wrapper for AgentLoop — adds memory retrieval and turn logging to messages.create calls. Supports streaming.
LangChain integration for AgentLoop — auto-logs turns to the review queue and provides a memory injection Runnable for retrieval.
Drop-in OpenAI SDK wrapper for AgentLoop — adds memory retrieval and turn logging to chat.completions.create calls. Supports streaming.
The intelligence layer for AI agents. Self-learning loops that make your agents smarter over time.
A Python package for managing AI agent memory systems with persistence and vector search