Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 39 of 41

dlightrag-memory

Reusable cross-conversation profile memory for DlightRAG

langgraph-checkpoint-objectstorage

LangGraph checkpoint saver backed by local filesystem, GCS, or S3 via fsspec

llamaindex-memorysync

MemorySync memory for LlamaIndex: a Memory subclass with durable server-side long-term memory, a recall memory block, a retriever, and agent memory tools.

memagent-local

Local-first layered memory and autonomous learning engine

multi-agent-archiver

Archive local AI chat histories to S3, freeing up disk space while keeping conversations searchable

orreth-agent

The lifeforce kit: give any agent an identity, a home floor, a memory, a governed mind, and a diary — and it appears in the universe.

pydantic-ai-memorysync

MemorySync memory for Pydantic AI: a drop-in agent capability that injects recalled context every run and sends each completed run's user prompt to fact extraction, plus typed memory tools and async helpers.

skillmem

Self-improving skills for Claude Code — your agent learns, recalls, reinforces, and forgets. SQLite + FTS5 + local embeddings + MCP.

tollmeshcache

Python SDK for TollMeshCache - Distributed CRDT-based caching

agent-resurrect-btw

Agent Resurrect SDK

entroptics-llm

Renamed: this package is now entroptics-context.

hermes-local-rag

Private local hybrid text and visual memory provider for Hermes Agent

memstrata-agent-hooks

One SDK for MemStrata conversational memory and agent governance hooks

remagent

Autonomous Zero-Vector Memory Framework for AI Agents with Biological REM Consolidation (Gemini, Anthropic, OpenAI-compatible, xAI)

smaran-agent-framework

Memory tools and middleware for Microsoft Agent Framework with Smaran

smaran-openai-sdk

Memory tools and middleware for OpenAI function calling with Smaran

cadet-brainstem

Cadet Brainstem — an orchestration + measurement layer that reduces AI-agent context consumption.

@unieai/uad-compaction

Abstract compaction service seam (ctx.compaction) for the DeepSeek Harness

agent-memory-cli

Cross-session memory for coding agents: plain files, git-native, no server

agent-memory-doctor

Boot-time integrity check for AI agent memory & convention files — catch silent convention loss, injection dilution, broken rollback anchors.

agent-memory-kit

Four small, dependency-free memory and safety patterns for LLM agents: scratchpad state, fuzzy recall, pre-compaction checkpointing, and permission boundaries.

agent-tx

Deterministic ACID transaction and rollback engine for AI agents in <1µs

agent-work-runtime

Persistent work state and minimal context for long-running AI agents

agentibrain

Standalone brain + knowledge-base kernel (agenti ecosystem)

calera-agent-memory

Plug-and-play topological memory substrate for LLMs, LangChain, and autonomous agent swarms.

meld

Ephemeral two-party context bridge. A pours context, gets a share link; B answers once on the page; A reads the merged exchange; content self-destructs (1h unresolved free). Free tier 3 melds/hour; $3.33 one-time extends a meld to 24h for async handoffs. HTTP API, MCP server, A2A card.

meld

Ephemeral context URL — puts the context on a URL so neither side has to paste the block. Then the URL dies.

screenpipe

Screenpipe review: compare features, pricing, use cases, access model, and alternatives for this Memory agent in 2026. Searchable computer history for people and AI assistants.

@ai-agent-memory/web

Local-first AI Agent Memory — inspection and management dashboard

@alvin0/ai-agent-sdk-instructions-node

Node filesystem-backed AGENTS.md context section for ai-agent-sdk

@itsamruth/orbit

Git for AI agent conversations.

@gamaze/hicortex

Persistent agent identity for AI agents — a hand-edited identity layer, nightly-distilled experience, and lessons injected every session, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, Pi, and opencode.

llm-wiki-kit

Local Markdown project memory for Codex, Claude Code, and opencode, with hook-based context and agent-reviewed knowledge.

n8n-nodes-tembory-agent-memory-v2

Tembory Agent Memory for n8n AI Agents

@shivam.dixit/token-budget-langchain

LangChain.js adapter for token-budget: BaseMessage[] conversion and a TokenBudgetMemory class — context window and token budget management for LangChain agents.

@hasna/mementos

Universal memory system for AI agents - CLI + MCP server + library API

@agent-context/sift

Compress LLM tool output, reduce context tokens, and recover lossy originals from a local stash.

conversationalist

A TypeScript library for managing AI conversation state

@yottameta/yotta-memory-plugin

Yuanyi (元忆) — boundary-aware, file-based memory for AI agents, packaged as a YottaMeta Agent Plugin.

@muxtsou/memory-cell

Cross-platform CLI and MCP cognitive runtime for AI coding assistants

akela

A deterministic context compiler for AI agents — evidence-driven context engineering beside your markdown knowledge base: agents propose, evidence gates, you decide.

@davesheffer/hunch

A shared record for AI agents: decisions, completed work, and commitments, with sources. Git-native engineering memory and a self-hosted state server.

@upstash/agentkit-ai-sdk

Upstash AgentKit adapter for the Vercel AI SDK: chat history, memory tools, Redis-Search tools, rate limiting, and cached tools.

@aliyunrds/ctxdb

Unified access layer for RDS ContextDatabase: `ctxdb` CLI (memory + KB ops), one-shot multi-agent installer, per-agent config, hooks/plugins, and SKILL.md.

contextum

AI context layer and multi-agent coordination center for any repository, exposed over MCP.

agentic-recall

Long-term memory for agentic tasks. It tells you when it doesn't know.

@dlcaio/langgraph-checkpoint-dynamodb

DynamoDB checkpoints for LangGraph with versioned channel storage, compression, optional S3 offload, and explicit recovery errors.

@mi8y/cap-agents-memory

CDS Plugin for LangGraph long-term memory stores in SAP CAP applications

fractal-memory

Hierarchical-graph long-term memory for AI agents: variable-depth abstraction tree, cross-topic recall, temporal knowledge graph. Ships an MCP server, an HTTP service, and a LangGraph BaseStore.

aesop-agentic

Deterministic archive and backup service for AI interaction histories.

agent-cabinet

Give your agent a filing cabinet.

agent-engine-sdk-memory

Slim public Memory facade and models for Atlas Agent Engine

agent-letter-bridge

Message the CLI agents on your machine from your phone — every message becomes part of their memory.

agent-memory-integrity

Agent Memory Integrity (agmi): a conformance test suite that measures whether AI agent memory and checkpoint stores notice tampering

agent-memory-kit-cli

Local memory, a codebase index, and working discipline for AI coding agents. Zero dependencies, no network.

agentbase-memory-agentscope

AgentScope long-term memory middleware backed by Agentbase Memory

agentevo-local

Agentevo local runtime (TZ-2): capture, DLP, encrypted vault, recall, guards, execution.

agentos-memory

The operating memory and learning runtime for AI agents — turn every execution into reusable intelligence.

coherence-membrane

Give AI agents inspectable observations of files, images, screens, and context with receipt-backed perception.

crewai-memory-core

Shared core for CrewAI unified-memory StorageBackend implementations — build a Memory backend with five small primitives

crewai-memory-cosmosdb

Azure Cosmos DB StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (VectorDistance)

crewai-memory-dynamodb

Amazon DynamoDB StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (SearchVectors)

crewai-memory-firestore

Google Firestore StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search (find_nearest)

crewai-memory-postgres

PostgreSQL (pgvector) StorageBackend for CrewAI unified Memory — hierarchical scopes, categories, metadata filters and native vector search

crewai_persistence_dynamodb

Amazon DynamoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

crewai_persistence_mongodb

MongoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

crewai_persistence_sql

SQL persistence backend for CrewAI Flows via SQLAlchemy (SQLite, PostgreSQL, MySQL) with built-in message pruning via agentstate-reducer

deepagents-graph-memory

Graph-backed context scratchpad for LangChain Deep Agents.

harborrag-memory

Scope-aware short-term, working, and long-term memory for HarborRAG.

langgraph-checkpoint-gridgain

GridGain checkpointer, store and node cache for LangGraph — short-term thread state, long-term cross-thread memory, and node-level caching.

langgraph-checkpoint-plainredis

LangGraph checkpoint savers on plain Redis (sync + async) - no RedisJSON / RediSearch modules required, works on Redis 5+

langgraph-memory

Long-term memory engine for LangGraph over any BaseStore — LLM fact extraction, consolidation, and recall ranked by semantic similarity, recency and importance (a maintained alternative to LangMem)

langgraph-singlestore

SingleStore checkpoint saver and store for LangGraph

langgraph-store-core

Shared core for LangGraph long-term-memory (BaseStore) backends — implement a store with four small primitives

langgraph-store-cosmosdb

Azure CosmosDB long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (Cosmos DB vector) search

langgraph-store-firestore

Google Firestore long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (Firestore vector) search

langgraph-store-postgres

PostgreSQL long-term-memory store (BaseStore) for LangGraph — namespaced key/value memory with filters, list_namespaces and native semantic (pgvector) search

llm-cache-redis

Lightweight semantic caching for LLM applications, backed by Redis.

llmgrid-context

Context assembly and memory for llmgrid

memanto-agentcore

Amazon Bedrock AgentCore Runtime adapter for Memanto persistent memory (preview)

mnem-agents

Version control for AI agent memory. Python SDK for Mnemosyne.

mnem-langgraph

LangGraph BaseStore backed by Mnemosyne: versioned agent memory with blame and branch.

mragent-oss

Pluggable open-source agentic memory layer — MRAgent (arXiv:2606.06036)

provena-agent-memory

Self-hosted MCP memory for AI agents with evidence-backed, explainable claims

pydantic-ai-cosmosdb-memory

Azure Cosmos DB MemoryStore for the PydanticAI harness Memory capability — CAS versions via ETags and idempotent operation receipts

pydantic-ai-dynamodb-memory

Amazon DynamoDB MemoryStore for the PydanticAI harness Memory capability — CAS versions and idempotent operation receipts via conditional writes

pydantic-ai-memory-core

Shared core for PydanticAI harness MemoryStore backends — CAS versions, idempotent operation receipts and bounded search over a few conditional primitives

pydantic-ai-pixeltable

Pydantic AI Harness MemoryStore and Pixeltable catalog tools.

pydantic-ai-postgres-memory

PostgreSQL MemoryStore for the PydanticAI harness Memory capability — the upstream transactional store, built from a connection URL with an owned asyncpg pool

recall-langgraph

Resume LangGraph agents from their own records, backed by Recall by Polign

slim-llm-memory

Slim, fast, persistent memory + retrieval for LLM apps. numpy + httpx, ~1000 LOC, drops into anything.

strata-agent-memory

Portable, auditable, cross-vendor memory for LLM agents: evidence-bound claims, trust tiers, and compiled context views.

taisce-agent-framework

Microsoft Agent Framework adapter for Taisce: a context provider that injects governed memory as one untrusted user message and records the turn afterwards.

taisce-langgraph

LangGraph adapter for Taisce: agent middleware that injects governed memory as one untrusted human message and records the turn afterwards.

tessera-agent-memory

TESSERA — Temporal Evolving State Synthesis with Explicit Relations and Atomic Memories: a text-first, auditable memory and evidence layer for AI agents.

kith

Social memory for multi-agent systems: who remembers what, about whom, visible to whom.

@canyuda/agent-sync

Sync AI agent sessions across machines via a git repository

@zidniryi/tupa

Stash and resume AI agent sessions across Claude Code, Codex, opencode, and more.

@centient/sdk

TypeScript SDK for Centient — AI agent memory and context engineering infrastructure

@oh-my-pi/snapcompact

Bitmap-frame context compression for vision-capable LLMs

More in Agent frameworks & infrastructure