Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 38 of 41
Gzip-based compression similarity for Swarmauri.
Synaptic Weight Eviction engine for dynamic LLM memory consolidation
Stale-context protection and source-aware code memory for AI coding agents
Docmancer review: compare features, pricing, use cases, access model, and alternatives for this Memory agent in 2026. Local AI agent memory tool with MCP server and plugins
MCP server and REST API for persistent, typed AI-agent memory.
Local-first multi-agent memory MCP. Shared SQLite + FTS5, secret-blocking, lite transport (no SDK by default), namespaces, batch + handoff tools.
Self-hosted multi-device, multi-agent session atlas
Sub-millisecond, local-first cognitive memory layer for AI agents — NumPy/BLAS-accelerated hybrid retrieval, Ebbinghaus decay, and knowledge compaction. Ships a premium React/Ink terminal UI plus the `izero` Python CLI bridge.
Amazon DynamoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer
Thin LangGraph node helpers for DMA memory.
AgentRAM-backed long-term memory for LangGraph and LangChain: a BaseStore plus agent-callable memory tools, no vector database.
LangChain retriever integration for MemStrata Conversational Memory
Azure CosmosDB backend for pydantic-ai-persistence — StepStore + message history for PydanticAI
Amazon DynamoDB backend for pydantic-ai-persistence — StepStore + message history for PydanticAI
Google Firestore backend for pydantic-ai-persistence — StepStore + message history for PydanticAI
Backend-agnostic persistence for PydanticAI — chat history + durable StepStore, over a small async KV interface
Typed sync and async client for the Shared MDStorage HTTP contract
Local hybrid retrieval (BM25 + embeddings + RRF) for agent memory and codebases — one SQLite file, MCP server included.
GitHub-repository Storage backend for Strands Agents — persists keys as versioned, diffable files in a repo.
MongoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory
SQL (SQLAlchemy) implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory
Amazon DynamoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory
Local CLI for finding and resuming AI agent sessions across local projects.
脑珊瑚 Coral Memory — 面向 LLM Agent 的热度感知记忆层(DeepSeek Harness 插件):MCP 记忆工具(memory_search/insert/thread_* 等 16 个)+ 设置面板(统计/容量/检索/配额)。作者:Mr. Code Muggle (@Ne)。
Abstract compaction service seam (ctx.compaction) for the DeepSeek Harness
Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness
Event-sourced session store for the DeepSeek Harness
JSONL durable session persistence backend for the DeepSeek Harness
Cross-session snapshot references and durable untrusted model context (ctx.sessionReferences)
Multi-tier cognitive memory module for nestjs-agentic enabling Short-Term, Scratchpad, and Composite memory stores.
memB - Local Offline Long-Term Agentic Memory
Coding Agent Harness SDK — 记忆与上下文管理
Database checkpointers for @langgraph-toolkit/core: SQL (SQLite/Postgres/MySQL), Redis, MongoDB. Drivers are injected, so no database library is a hard dependency.
Event-sourced experience capture, validation, and reuse for AI agents.
Local markdown memory & cross-agent context engine for coding agents (MCP).
Areev storage backend for CrewAI memory: supersession-based updates, audited deletes, and right-to-erasure over memory sources
Areev persistence for LangGraph: a BaseStore and a BaseCheckpointSaver over content-addressed, governable memory files
Microsoft Agent Framework chat history backed by Citadel: encrypted at rest, with deletes that destroy the key
OpenAI Agents SDK sessions backed by Citadel: encrypted at rest, with deletes that destroy the key
Strands Agents session storage backed by Citadel: encrypted at rest, with deletes that destroy the key
Cortadel memory for CrewAI — self-hosted long-term temporal graph memory as a drop-in crewai.Memory, plus native tools.
Cortadel long-term graph memory as a native Pydantic AI capability — memory tools plus automatic recall and persistence.
MongoDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer
SQL persistence backend for CrewAI Flows via SQLAlchemy (SQLite, PostgreSQL, MySQL) with built-in message pruning via agentstate-reducer
A DynamoDB-backed BaseStore for LangGraph — cross-thread memory for agents, no Postgres/pgvector required
Itsuki long-term memory block for LlamaIndex.
Context-Memory Harness for AI Agents. Context Window = RAM, Local Wiki = Disk.
Identity-aware Nowledge Mem connector for LangGraph and LangChain agents
PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory
MongoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-mongodb-storage)
PostgreSQL implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory (aka strands-postgres-storage)
A filesystem-native, version-controllable long-memory paradigm for AI agents. Surface/Middle/Deep layers + recall/writeback/consolidate protocol. Pure Markdown, zero infra, drives agent self-evolution.
CrewAI adapter for tracegc context compaction
LangGraph adapters for tracegc
Storage adapters for tracegc
Object storage plugin (RFC-0019, M9): S3, Azure Blob, GCS, OneDrive behind one ObjectStore contract
Terminal UI binary for the Real Memory AI Agent CLI (linux/x64).
Terminal UI binary for the Real Memory AI Agent CLI (win32/x64).
Terminal UI binary for the Real Memory AI Agent CLI (linux/arm64).
Terminal UI binary for the Real Memory AI Agent CLI (darwin/arm64).
Terminal UI binary for the Real Memory AI Agent CLI (win32/arm64).
The production framework for self-improving & self-organizing LLM knowledge vaults — grounding invariants, code drift detection, auto-skillification, and 1-click multi-agent setup.
Automatic long-term memory for Vercel Eve agents — Hindsight memory injected before each turn and retained after, with no model tool-calling
Coding-agent orchestration and MCP context runtime with governed repository execution, bounded tool results, and multi-agent session management.
Experience learning, trajectory reflection, and self-correction engine for nestjs-agentic.
Cortadel long-term memory for LangGraph — a BaseStore implementation, memory tools, and automatic recall/persist graph nodes.
Intelligent context layer for Claude Code — infinite session memory, minimal active context
MemorySync memory for CrewAI: a native StorageBackend for Memory(storage=...), agent memory tools, and recall context for tasks.
MemorySync integration for LangChain: chat message history, memory tools, and recall context.
MemorySync memory for the OpenAI Agents SDK: a drop-in Session implementation with durable server-side history, long-term memory instructions, and agent memory tools.
CLI for Tages AI agent memory
Mnemo-backed long-term memory for LangGraph JS — a BaseStore implementation plus remember/recall tools.
Optional exact and semantic answer-cache primitives for Inupedia Spotlight
Use AegisDB as a LangGraph long-term-memory store
Factory for building LangChain deepagents equipped with episodic, semantic, and procedural memory.
Khwan memory for CrewAI — recall/remember/verify as tools, and a prepare→record wrapper around a crew run. Khwan never runs your model.
MongoDB Atlas-backed virtual filesystem search adapter for LangChain DeepAgents
The sleep cycle for AI memory: every memory carries its evidence; a scheduled pass keeps the evidence honest.
Local-first AI agent memory system. No account needed.
Cadet Token Saver — an orchestration + measurement layer that reduces AI-agent context consumption.
Terminal UI binary for the Real Memory AI Agent CLI (darwin/x64).
Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.
MemorySync integration for LangChain.js and LangGraph.js: chat message history, memory tools, recall context, and a LangGraph store.
Proactive semantic memory and mid-run steering for the Pi coding agent
SGME memory engine bridge for DeepSeek Harness — multi-agent shared long-term memory via HTTP.
Local-first Rust memory service for multi-agent workflows — prebuilt-binary installer.
A portable, long-term agentic memory MCP server — a thumb drive for your AI context.
The runtime layer for Agentic AI. Persistent memory, autonomous agents, and workflows that survive every session.
A Pi extension that keeps long-running agentic sessions on track with background memory, contemplation, and structural review.
Archive local AI chat histories to S3, freeing up disk space while keeping conversations searchable
Encrypted, capability-scoped, versioned Markdown file-tree memory for MCP agents
MemorySync for Microsoft Agent Framework: a ContextProvider with budgeted instruction-layer recall, per-run identity, once-per-turn duplicate-proof capture, and fail-open everything.
Governed project memory for AI coding agents across sessions and tools
Evidence-first tools for validating AI agent persistence publications and probing durable state serialization
MemorySync for Microsoft AutoGen: an async-native Memory implementation with a hard recall budget, role-aware retrieval, duplicate-proof fact capture, and session-scoped clear.
MemorySync reference architecture for AWS Bedrock agents: a memory-augmented Converse loop and a Bedrock Agents action-group Lambda — the first vendor action-group memory integration.
Local, automatic memory for Claude Code. Remembers past sessions in 0.7s for ~2.5k tokens instead of 211k. Nothing leaves your machine.
CNB Issue 智能体记忆系统(cnb-agentic-memory)是基于 CNB 平台构建的通用记忆工具,把 CNB 的 issue、知识库、检索能力组合成一个开箱即用的智能体记忆层。
LangChain BaseMemory adapter for Context-M — the Universal Neuro-Symbolic Memory Fabric.
Verifiable semantic recovery layer for long-running AI agents.