Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 35 of 41

cluxion-Agentplugin-AutoClearMemory

Universal agent memory plugin (ForgetForge): recall-centric retention, tiered forgetting, Rust scoring engine for Hermes, Claude Code, and Codex.

hindsight-haystack

Haystack integration for Hindsight - persistent memory for AI agents

hindsight-superagent

Superagent safety integration for Hindsight - guard and redact memory operations

llmbuffer

Cache-optimized LLM conversation history management with static/dynamic system prompts, transition modes, and compaction hooks.

pyagent-context

Three-tier memory with trust-aware context ledger for multi-agent LLM systems

@sankalpasarkar/grwm

Get Ready With Me - The universal AI agent handoff tool. Never explain your codebase to a new agent again.

agentcairn

Local-first agent memory: an Obsidian markdown vault as source of truth, with a rebuildable DuckDB index.

langgraph-tenancy

Tenant isolation and per-tenant usage metering for LangGraph checkpointers and stores

hipcortex

TypeScript & Node.js SDK for HipCortex - the persistent causal memory & token optimization substrate for autonomous AI agents.

memnet-llm

Mission working memory for LLM agents: session graph + pin_map, not a RAG corpus

@in-sp3ctr3/mempr

Pull requests for AI memory.

agentcheckpoint

MCP checkpoint server: atomic state coordination for AI agents, cron workers, and multi-agent systems

hindsight-agent-framework

Microsoft Agent Framework integration for Hindsight - persistent memory for AI agents

lethe-llm-context

Context garbage collector for long-running LLM agents — offload and recall to save tokens (Claude Code & Codex via MCP)

perseus-agent-core

Shared memory and tool layer for Perseus agents — MemoryEntry, Elastic/Engram backends, decision log, knowledge graph, project context.

@agentstate/sdk

TypeScript SDK for AgentState — conversation history for AI agents

claude-context-bridge

Persistent memory for Claude Code — checkpoint-based replanning across sessions

llama-index-memory-recollect

LlamaIndex memory integration for Recollect

supermemory-agent

SuperMemory: MCP-first learning memory layer for Claude, Cursor, and agent workflows

supermemory-agent-mcp

SuperMemory: MCP-first learning memory layer for Claude, Cursor, and agent workflows

opencode-fractal-memory

Fractal memory system for OpenCode with semantic search and automatic compression.

@halo-format/langgraph

Halo host adapter for LangChain agents and LangGraph graphs: a wrapToolCall encode middleware (results become a shape map, out of context) plus a single halo_fetch navigation tool. installHalo() wires it in one call.

ilma-agent

Framework-agnostic agent memory system — Postgres + pgvector + MCP

mnemosyne-langchain

LangChain and LangGraph integration for the Mnemosyne memory substrate. BaseChatMessageHistory, BaseMemory, and BaseRetriever adapters with hybrid BM25+vector recall, per-session thread tracking, automatic redaction, TTL support.

@wutangbanger/horus-insight-store

JSONL-backed persistence for AI agent insights

tokencompress

Automatic token compression for AI agent tool outputs. 60-90% fewer tokens, full explainability.

wyrm-mcp

Local-first persistent memory for AI agents over MCP. Ground truths, negative learning (recorded failures block repeats), decision causality, hybrid recall, live memory streams, run-attributed fleet memory — a structured SQLite memory on your machine, no

headroom-ai

Compress tool outputs, logs, JSON and chat history before each LLM call. Fewer input tokens, same answers. Adapters for OpenAI, Anthropic, Gemini and the Vercel AI SDK. Runs against the local Headroom proxy (pip install "headroom-ai[proxy]").

langchain-unison

LangChain integration for the Unison Brain — memory, chat history, and retriever

llama-index-memory-unison

LlamaIndex memory provider backed by the Unison brain — long-term agent memory via a knowledge graph.

llmslim

Context compression and planning for RAG and AI agents: fit retrieved documents, chat history and tool output into a token budget.

mimir-crewai

Mimir persistent memory tool for CrewAI agents

mimir-langgraph

Mimir persistent memory backend for LangGraph agents

mnemosyne-autogen

AutoGen v0.4 MemoryStore adapter for the Mnemosyne memory substrate. Implements the MemoryStore protocol with per-agent container scoping, hybrid BM25+vector recall, async support for high-throughput multi-agent runs.

mnemosyne-crewai

CrewAI long-term memory adapter for the Mnemosyne memory substrate. Implements the LongTermMemory protocol via duck typing, with per-agent and per-task scoping, hybrid BM25+vector recall, idempotent writes.

mnemosyne-openai-agents

OpenAI Agents SDK lifecycle hooks for the Mnemosyne memory substrate. on_turn_start, on_turn_end, search, and store hooks backed by the substrate, container-scoped, with automatic redaction.

slim-agent

Self-Learning Index Memory for AI agents

@chibakuma/agent-memory-hall

MCP-native memory server with built-in governance for AI agents

@retaindb/sdk

TypeScript SDK for RetainDB - the memory bus for agentic systems

@dory-agentic/dory-agentic-sdk

Dory Agentic SDK: LFS context management with AI SDK tool loops for long-running agents

@dawn-ai/sqlite-storage

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

agent-checkpoint-framework

Never lose work when an agent fails.

agent-nerve

Shared operational memory and coordination for mixed AI agent fleets.

llm-context-compressor

Shrink LLM context windows by removing noise, redundancy, and long-tail detail — without losing signal.

opengater-storage-client

Client library for the opengater-storage service

stenotype

Automatic memory capture and recall for AI agent workflows

@oh-my-pi/pi-mnemopi

Local SQLite memory engine for omp agents

@memfork/langgraph

LangGraph checkpointer adapter for MemForks — anchors agent state on Sui with branch-aware memory.

agent-dreamer-sdk

Agent Memory HTTP SDK and lightweight Agent adapter

Pieces.app: Ambient Artificial Memory

Pieces is a private, on-device, long-term memory layer for macOS, Linux, and Windows that proactively captures your work context as it happens. Over time, Pieces becomes your very own “internet of all context”—browse your artificial memories in the Pieces Desktop app, or plug them into the agents you already use: OpenClaw, Hermes, Claude, Cursor, Codex, etc.

@memlink/cli

Memlink — MCP server for persistent AI agent memory. Self-hosted, one URL, no cloud.

agentic-workspace-core

Repository-native agent memory, skills, AGENTS.md, llms.txt, and knowledge workflows for coding agents.

agent-memory-contracts

JSON Schemas and Python contracts for AI agent memory integrity: evidence, candidate, ledger, taste, state, and ContextPack planes.

agent-virtual-shell

A virtual shell-over-database filesystem for AI agents: a strict, append-only memory layer with a frozen shell dialect.

agentmemo-py

Persistent memory for AI agents — store, retrieve, and recall context across sessions.

agentpub-py

Collective knowledge store for AI agents — publish facts at runtime, query shared learning

agentrelay-memory

AgentRelay Secure Memory Persistence and Recall integrations for AI frameworks.

new-agent-memory

Explainable human-like memory layer for AI agents.

openclaw-memgpt-sidecar

MemGPT memory architecture as a Python sidecar for the openclaw-memgpt plugin. Includes Anthropic/Claude compatibility patches against the original MemGPT (Apache 2.0).

@memfork/core

Git for AI agent memory — TypeScript SDK for MemForks on Sui

@grubgenie/openviking-memory-layer

OpenViking memory adapters for LangChain.js and LangGraph.js — retriever, store, agent tools, chat history, and context middleware.

@strvmarv/total-recall

Multi-tiered memory and knowledge base plugin for TUI coding assistants

agentrecall-db

Agent memory in a single SQLite file — no vector DB, no server, no cloud. Keyword recall on stdlib alone; torch-free hybrid semantic search via model2vec + sqlite-vec. Python lib + MCP server + CLI.

datacules-agentdb

Single-file embedded database for AI agents. SQL + Vector Search + Full-Text Search + Hybrid Queries + Memory Graphs.

icm-llm

O(1) hyperbolic memory for any LLM — 260 bytes per session forever

abmind

Standalone AI agent memory system — SQLite, FTS5, embeddings, 4-layer recall, sleep maintenance

@hypabolic/pi-hypa

Pi extension that keeps noisy tool output out of your context window. Automatically rewrites shell commands through Hypa for local, deterministic compression, context-aware file tools, and recoverable evidence.

@locusgraph/client

TypeScript SDK for LocusGraph memory system with LangChain integration

agentcrdt

Semantic-causal CRDT for agent-mutable world state

claude-memory-engine

Reusable lessons/memory engine for Claude Code: frontmatter lessons, auto-CATALOG, offline retrieval, path-triggered lessons, auto-maintenance, parallel-session and sub-agent guards.

deepagents-okf-backend

OKF-aware virtual filesystem backend for LangChain Deep Agents (Open Knowledge Format).

distil-llm

Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test.

@animakit/homeostasis

Give your LLM agent a mood — Yerkes-Dodson stress modeling, Russell affect mapping, allostatic regulation, and a self-tuning 3-arm bandit. Sub-µs core ops, every op <1ms, 0 tokens, fully serializable.

anansi-langchain

LangChain + LangGraph integration for Anansi — retriever, memory tools, and graph-state memory annotation

anansi-tools

Framework-agnostic memory tools for Anansi — remember/recall tool definitions for the Vercel AI SDK, OpenAI function calling, and any agent framework

@k3_2o/pi-chrollo

Agentic memory for Pi — verbatim session capture + grep retrieval

@zbs-gg/pulse

Pulse portable memory for AI agents: MCP server (pulse mcp) + installer/CLI in one package.

@chibakuma/aca-langgraph

ACA-governed checkpointer for LangGraph.js — adds source_tier, provenance, namespace isolation, and audit trail to LangGraph state

agent-skill-system

A zero-dependency skill memory, testing, and refinement engine for AI agents.

omni-agent-memory

OmniAgentMemory — a namespaced, structured memory service for Claude Code and other agents

@mnemosyne-eurydice/langchain

LangChain.js BaseChatMemory implementation backed by Mnemosyne. Persistent, searchable, container-scoped chat history with hybrid BM25+vector recall. Replaces LangChain's in-process BufferMemory and ZepMemory. Per-conversation thread tracking, automatic r

@honcho-ai/vercel-ai-sdk

Honcho memory for the Vercel AI SDK -- persistent identity, theory-of-mind, dialectic reasoning

langgraph-checkpoint-tigris

Library with a Tigris object-storage implementation of LangGraph checkpoint saver, with zero-copy bucket-fork branching.

openclaw-hybrid-memory

Give your OpenClaw agent lasting memory: structured facts, semantic search, auto-capture & recall, decay, optional credential vault. Part of Hybrid Memory v3.

langchain-hyperspace

Official LangChain.js and LangGraph.js integration for HyperspaceDB

@upstash/agentkit-eve

Upstash AgentKit adapter for the Vercel Eve agent framework: memory tools, an Upstash Redis memory backend and provider for eve memory slots, Redis-Search tools, a rate-limit gate, an Upstash Box sandbox backend, and cached tools.

openclaw-amem

A-MEM agentic memory backend for OpenClaw — TypeScript rewrite

bluetemberg-agents-agentic-specialist

Agentic systems specialist agent for Bluetemberg — agent memory design, state management, orchestration patterns.

hystersis

Persistent memory infrastructure for AI agents - Memory that adapts. Intelligence that compounds.

agentforge-memory-kuzu

Embedded, file-backed GraphStore for AgentForge (Kùzu)

memory-forge

Forge persistent memories for your AI agent. 9 MCP tools + 5 auto-engines. Powered by Shelby decentralized cloud.

@ayberkaya/memshot

Tiered, token-budget-aware memory for any LLM agent

agent-cache-optimizer

OpenCode plugin for LLM prompt caching, token savings, and KV cache reuse across AI agent sessions

turbomem

Embedded memory for TypeScript agents. Local-first by default. Pluggable to edge and serverless. Extract facts, embed them, and recall scoped memories from your app process, with pluggable vector storage and framework adapters.

@remem-ai/remem

Local-first coding agent memory for Claude Code and OpenAI Codex

agenticow

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory. Branch a base memory in ~0.5ms / 162 bytes regardless of base size — 83x faster, 3000x smaller than full-copy snapshots. Exact read-through queries (parent ∪ edits, chil

pi-vault-mind

Passive Obsidian vault extension for pi. Watches @agent markers, dispatches forked subagents (Miner, Broadcaster, Heavy-Lifter), stores in LanceDB with vector + FTS + graph. Multi-agent 'Drop & Forget' workflow for the pi agent ecosystem.

@ayushkumar320/codebuddy

Local-first Markdown-backed MCP memory and automatic project-context engine for multi-agent coding, indexed with Postgres and pgvector.

eve-memory

Cross-session memory layer for the Vercel eve agent framework

eidetic-mcp

Eidetic — Agentic Memory MCP Server

More in Agent frameworks & infrastructure