Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 40 of 41
Durable conversation, task, and document runtime for Pi
Autonomous AI agent tool and MCP server for semantic token compression and L402 edge solvency clearance.
Mark: Metacognitive Artificial Relational Knowledge AI
Efferent composable agent framework, 0.22.0. Bun only.
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
SQLite persistence adapters for the Agent framework
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Memory product - context builder, embedding cache, tiered memory
Memory product - context builder, embedding cache, tiered memory
Myrmo SDK: shared memory of solved errors for AI agents. Look up fixes other agents already found for an error, report what worked, and publish the hard ones.
Oracle AI Database integration for LangGraph
Durable LangGraph conversation records and Agentdock synchronization
TypeScript SDK for INITE Brain — a typed client, framework-shaped tools for the Vercel AI SDK and friends, and a LangGraph-shaped store. Long-term memory for agents: bitemporal facts, hybrid retrieval, citations.
Scaffold a local-first AI-agent memory app powered by actrone-memory: zero services, no API key.
ACLA Agentic Context Runtime: persistent project context, a deterministic Context Compiler and governed Mission Working Sets for AI agents, with lifecycle, observation, REST, UI and MCP surfaces.
Shared task memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
Shared, git-backed memory for Claude Code and Codex.
Governed memory layer for AI agents
Agentics SDK for Python: shared memory for AI agents, receipts and the gateway.
Canonical AgentOS State Ledger client and content-addressed blob storage
Context, memory, documentation RAG and observability umbrella for autonomous coding agents
Unified multi-device cloud synchronizer for ~/.agents (memory, skills, docs, traces, identity).
Code Craft AI - Storage Database
Shared, durable memory for coding agents across projects and machines (MCP + CLI over SQLite)
HydraDB external-memory storage for CrewAI agents.
past dev for CrewAI: Ingest and Recall as crew memory and as agent tools.
CrewAI integration for Recall, long-term memory for AI agents: tools to search, ask and remember, and memory as task context.
GoodMem integration for Microsoft Agent Framework.
GoodMem memory and tools for the AutoGen agent framework.
GoodMem knowledge storage and RAG tools for CrewAI agents
GoodMem integration for DSPy
LangChain integration for GoodMem: long-term agent memory with semantic storage and retrieval.
LangGraph integration for GoodMem: long-term agent memory with semantic storage and retrieval.
Native LlamaIndex retrieval, Document ingestion and agent tools for GoodMem.
Captura automática de sesiones y herramientas de Hermes hacia AgentMemory
Adaptadores de LangChain y LangGraph para HiveDB: VectorStore, historial de chat y BaseStore de memoria a largo plazo.
LangChain custom tool integration for the Fodda Context Layer
Geniffy for LangChain: a memory of each of your users, for any LangChain agent. Middleware, tools and a retriever.
LangChain and LangGraph integrations for Gnarl agent memory
HydraDB integration for LangChain: persistent memory and retrieval.
MeMorae memory and retrieval adapters for LangChain and LangGraph
LangChain and LangGraph integration for Recall, long-term memory for AI agents: chat history, retriever, tools and agent middleware.
ScaleDown summarization, compression, tool-output compression, and extraction middleware for LangChain agents
Shared-budget extractive context trimming for LangChain.
Model-agnostic LangChain middleware that keeps only the last N conversational turns, without splitting tool_call/tool_result pairs.
LangGraph checkpointer and long-term memory store backed by HotKV, a RESP2/RESP3-compatible in-memory data store with built-in AI and LLM-serving features.
LangGraph long-term memory on MinnsDB: a store that keeps every version, and graph memory that knows which facts are current.
Qdrant-backed long-term memory store for LangGraph.
Geniffy for LlamaIndex: a memory of each of your users, for any LlamaIndex agent. A memory block and tools.
LlamaIndex memory block and retriever for Gnarl agent memory
past dev memory block for LlamaIndex agents: recall and ingest long-term memory with the past dev Memory API
past dev tools for LlamaIndex agents: recall and ingest with the past dev Memory API
Cross-model session migration for LLM conversations
Keep AI assistant chats, memories and instructions in one git repo, with secrets redacted and checked.
E2E encrypted LLM conversation sync service
Pydantic AI tools and integration for Memanto's persistent memory
Memanto long-term memory backend for NVIDIA NeMo Agent Toolkit
Geniffy for the OpenAI Agents SDK: a memory of each of your users, for any agent. Memory in the instructions, and tools.
OpenAI Agents SDK integration for Recall, long-term memory for AI agents: a session backed by Recall, memory tools and instructions.
Conversation persistence for pydantic-ai-app-factory, backed by pydantic-ai-harness StepPersistence
Google Firestore MemoryStore for the PydanticAI harness Memory capability — CAS versions via transactions and idempotent operation receipts
Durable, tenant-scoped long-term memory for LLM applications: typed entries with trust labels, SQLite full-text search, optional vector and hybrid search with your own embedder, supersession of changed facts, per-scope export and erase, and an optional tamper-evident audit log. Standard library plus ragleap-security. Single-tenant is one fixed scope. Not independently audited.
One searchable memory of your Claude Code, Codex and Cursor chats, exposed to every agent over MCP.
Typed, correctable long-term memory for Pydantic AI agents, backed by Recall by Polign
A small example package
Python SDK for SwarmV: edge vector memory with built-in access control for AI agents.
Async persistent LangGraph memory with exact namespaces and structured search.
CrewAI adapter for VantaDB — embedded vector memory for AI agents
DSPy adapter for VantaDB — embedded vector memory for AI agents
Haystack adapter for VantaDB — embedded vector memory for AI agents
LangChain adapter for VantaDB — embedded vector memory for AI agents
LlamaIndex adapter for VantaDB — embedded vector memory for AI agents
Opt-in XMemo context and capture for Microsoft Agent Framework
Files on local disk, in memory or in object stores, behind one async interface.
A Storage provider for S3-compatible object stores, proved against the shipped conformance suite
Tree-shaped durable sessions for Apeira agents.
Membase long-term memory for Microsoft Agent Framework (Python): a context provider with time-boxed recall and deliberate save/search/profile tools.
Local-first, shared long-term memory for AI agents: one SQLite database for Claude Code, omp and any MCP client
Persistent state for AI agents: files, JSON, and tool history in SQLite
Membase long-term memory for LangChain and LangGraph: a retriever, agent tools and a recall middleware.
Memory and mood for AI companions that outlive any one model: one SQLite file, usable by every LLM
Core engine for Totem, the local-first toolkit that keeps AI-agent work queryable, enforceable, and derivable as plain files in your codebase
Algorithmic conversation compactor for pi - transcript-preserving structured summaries, no LLM calls
Shared project memory and workflows for teams building with AI: a versioned record of plans, decisions, contracts and reviews across repos, human-approved review gates, and a zero-dependency `yad` CLI plus 38 skills for your AI assistant.
Session, run and handoff stores for BanglaClaw
PostgreSQL storage for BanglaClaw (Drizzle): sessions, runs, keys, audit and checkpoints
Pydantic AI capability that connects an agent to Glen's shared team memory
Security-first memory for AI agents: scoped tiers, taint tracking, tenant isolation and reviewed consolidation.
Local-first coordination bus for multi-agent CLI coding workflows (name reservation placeholder - real release ships with 0.1.1)
Shared, persistent memory for any AI agent. Agents recall what your workspace established — instructions, decisions, facts, preferences, active working threads, and grounded PDF/DOCX/CSV/web documents — before they act, then report outcomes so confidence
Durable, runtime-agnostic agent session state for React: pending approvals that survive reload, resumable stream cursors, subagent trees, and token/cost accounting — one event log, any transport.
Namespace protection for an internal NVIDIA BCM Python distribution
MongoDB-backed SessionStore for the Claude Agent SDK
LangChain tools for WITAN: look up errors and operational facts other agents measured, and query versioned datasets
Standalone LangGraph CheckpointSaver & Cross-Thread Store backed by HyperspaceDB CSR KAG Graph and Lorentz Hyperbolic Manifolds
LangGraph checkpointer backed by the SAP HANA Agent Memory Service
Persistent namespaced agent memory backed by Antfly