Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 37 of 41
An append-only, auditable ledger for LLM agent memory.
Local-first, MCP-native memory engine for AI agents with RAM cache and context-budgeted recall.
Unified pgvector-backed CLI for agent notes (breadcrumbs, memories, reflections) shared across the sf2 constellation
StateSync — the global state database for AI coding agents. Two-line SDK to unify memory across Cursor, Claude, OpenAI and Emergent.
A Python REST + WebSocket + MCP cache server for AI agents, backed by SQLite
A proactive memory layer for long-horizon coding agents, it knows when to remind.
Persistent memory for AI agents in two API calls. The official Python SDK for AgentRAM.
独立于具体 Agent 的持久化记忆层 (MCP Server),可被 Claude Code / Qoder / Cursor 复用
Code-first agent memory SDK for AideMemo (aidememo)
Event-sourced memory and orchestration server for multi-agent AI systems
Argon adapters for AI agent frameworks: sandboxed, versioned MongoDB for LangGraph and Mem0
LangChain integration for Attestari — the auditable memory layer for AI agents.
Query-aware context trimming for LLM requests. Your context could use a trim.
Context apoptosis for LangChain: µs-scale, class-aware history pruning (B.I.O.M.A. kernel) as a drop-in Runnable.
MongoDB Atlas-backed StorageBackend (memory store) for CrewAI's Unified Memory System.
DinoMem integration for CrewAI — drop-in memory tools for any Crew agent
Official Python SDK & Local-First RAG Memory Engine for AI Agents
Karpathy-native local Markdown wiki memory provider for Hermes Agent
Agent development kit for building self-tuning AI agents with HippoDb biological memory
InfoLang-backed memory storage for CrewAI's unified Memory system.
InfoLang memory Session for the OpenAI Agents SDK.
Give your LangGraph agent a June memory — mirror chat history from any LangGraph checkpointer into a searchable, cited June knowledge canvas. Three commands, no code changes.
Give your OpenAI Agents SDK agent a June memory — wrap any Session to mirror conversations into a searchable, cited June knowledge canvas, add a memory-search tool, and backfill existing session databases.
LangChain integration for Coalent — use any LangChain VectorStore/retriever, embeddings, and chat model as the substrate of a provenance-invalidated cognitive cache.
Reversible distil context compression for LangChain and LangGraph
LangChain integration for the Taguru long-term semantic memory server
DM Database checkpoint and Store persistence for LangGraph.
LangGraph checkpointer backed by inspeximus: durable thread state with queryable value history and receipted erasure.
Library with an OceanBase/MySQL implementation of LangGraph checkpoint saver with Elasticsearch vector search support.
LangGraph checkpoint saver backed by Upstash Redis (REST API)
LangGraph BaseStore backed by inspeximus: drop-in for InMemoryStore, plus queryable value history and receipted erasure.
LangGraph BaseStore backed by mnestic — embedded agent memory with atomic batches and one-call BM25+vector hybrid search.
LangGraph memory tools for VelesDB: drop the why() knowledge-graph memory wedge into any LangGraph agent.
LangGraph checkpoint saver for Amazon DynamoDB with built-in message history pruning via agentstate-reducer - single table, auto create, TTL and delete handling
Selective memory layer for AI agents: importance-scored, self-decaying, pluggable.
LangGraph BaseStore adapter and swarm client for Lithtrix agent memory
InfoLang memory integration for LlamaIndex
Fit chat history into any model's context window: token estimation, sliding-window packing with a running summary, and overflow detection. Zero dependencies, no AI inside.
Pack the most important text into a fixed LLM context-window token budget.
A personal, local-first memory store for LLM applications and agents
Python SDK for Lore — coordination memory for multi-agent AI systems: create runs, write events, and fetch read-your-writes context packs.
Recognizable alias for m3-memory's LangChain / LangGraph integration (drop-in Mem0 replacement, M3Store, M3Saver checkpointer, retriever, LCEL). Re-exports m3_memory.langchain.
Synap memory integration for Smolagents — memory tools and a turn recorder
Synap memory integration for Strands Agents — long-term memory, short-term context, and real-time anticipation
Durable Anthropic Messages adapter for the MemoFlow Python SDK
Durable OpenAI Responses adapter for the MemoFlow Python SDK
Poison-resistant, Byzantine-fault-tolerant shared memory for Microsoft AutoGen agent teams — implements the autogen_core Memory protocol; one rogue agent can't corrupt the team's recall.
Poison-resistant, Byzantine-fault-tolerant shared memory + robust voting tools for CrewAI crews — one rogue agent can't corrupt what the crew remembers or how it votes.
Poison-resistant, Byzantine-fault-tolerant shared chat memory for LangChain agent swarms — one prompt-injected agent can't corrupt the shared history.
Mengram memory tools for CrewAI agents — semantic, episodic, and procedural memory (workflows that learn from failures).
Local-first shared long-term memory for multiple AI agent CLIs
Kestrel: a local-first, memory-native AI engineering agent runtime.
Persistent, branch-aware, git-anchored memory & context layer for coding agents.
Python port of @earendil-works/pi-storage-sqlite-node — SQLite session storage backend
LangChain integration for the Progress Memory SDK
Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention
A pluggable memory layer for LLM agents with usage verification, contradiction resolution, and multi-tenant access control
Persistence ports for Roborean projects and runs
JSON/YAML filesystem persistence for Roborean
SQLAlchemy persistence adapter for Roborean
Gestor de contexto para agentes IA basado en grafos comprimidos generados desde Markdown
Spectron agent memory for the OpenAI Agents SDK
Spectron agent memory for Pydantic AI: toolset, auto-recall history processor, and persistence helpers.
Spectron agent memory as tools for the Strands Agents SDK.
Backend-agnostic session management for Strands Agents — a SessionStorage interface + KeyValueSessionManager to build session backends (DynamoDB, Redis, MongoDB, …)
Amazon DynamoDB storage backend for the Strands Agents SDK
Time-aware semantic LLM cache — automatically invalidates stale AI answers
Shared memory and skills across Claude Code and Codex
Architectural memory system for autonomous coding agents.
ZaniiDB Agent Memory - layered long-term memory (L0-L3) for AI agents: SQLite + hybrid BM25/vector recall, LLM extraction pipeline, FastAPI gateway, Python SDK.
Local-first archive, search, and recall for AI-agent conversations.
Brain-inspired associative memory layer for an LLM agent. Automatic (implicit) tier: capture -> embed -> recall. Codename Factor-X.
Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every memory keeps its source, its scope, and the evidence th
Neo4j Labs: TypeScript client for the Neo4j Agent Memory Service (NAMS)
A context-compression plugin — small context windows (a 100K context is enough), 5x fewer tokens, month-long single sessions (billions of tokens), and compression quality — for all agents: pi, OpenCode, Codex, Claude Code, and more. billion-context is all
Local-only agent memory store CLI
JavaScript SDK for the Backboard API - Build conversational AI applications with persistent memory and intelligent document processing
Conversation memory skill for multi-agent AI workflows — store, share, and recall across sessions and agents
XRLF Protocol — Universal OpenAI-compatible proxy that gives any LLM foveated ring memory, active recall, and cognitive steering. Point LM Studio, Ollama, or any OpenAI SDK at http://127.0.0.1:8300/v1 and it just works.
Proof-carrying memory for any agent framework — gate memory before generation, get an Answer Receipt. Adapters for LangGraph, the OpenAI Agents SDK, and anything else.
Your agent's decisions survive the session - append-only decisions with SUPERSEDES chains
Evidence-driven reasoned and learned decisions for AI agents with inspectable autonomy.
AgentMemory 微服务的 Python 客户端 SDK
面向 LangChain / LangGraph 开发者的 AI Agent 三层记忆管理微服务
SQLite persistence adapter for bysulf runs
CrewAI memory backed by Citadel: encrypted at rest, with deletes that destroy the key
LangGraph store backed by Citadel: encrypted at rest, semantic search, cryptographic deletes
Cognee memory provider plugin for Hermes Agent. After installing, run `hermes memory setup cognee`; Cognee Cloud needs nothing else, local mode runs cognee from a private environment the plugin installs on request.
Local-first graph memory for AI agents: embedded Cypher engine, MCP tools, cited budget-bounded retrieval and versioned project memory
Turn any agent into a self-learning system that learns from user feedback - safely, with two lines of code.
YantrikDB integration for LangChain — cognitive memory as a VectorStore and ChatMessageHistory. Stored memories decay, consolidate, and get contradiction-checked.
LangGraph checkpoint saver backed by Supabase (Postgres via PostgREST).
LangGraph BaseStore implementation backed by Upstash Redis (REST client).
Paritok context compression as a LiteLLM Proxy callback — tool filter + content/history compression + non-destructive recall + edit recovery, transparently on every request through LiteLLM Proxy.
A self-healing local-LLM wiki that compounds your documents across working, episodic, semantic, and procedural memory tiers.
Synap memory integration for deepagents — a memory backend, retrieval middleware, and tools
Model-agnostic text agents with associative graph memory, consolidation and dataset export
Needlepath context selection for LangChain agents (AgentMiddleware) and LangGraph.
Installs saihm-adapters[crewai], the consolidated package that now holds the SAIHM CrewAI adapter. Import from saihm_adapters (was saihm_memory).
Installs saihm-adapters[langgraph], the consolidated package that now holds the SAIHM LangGraph adapter. Import from saihm_adapters (was saihm_memory).