Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 41 of 41
Python SDK for SeaArt agent-gateway session history and memory APIs
Markdown-based AI memory system with multi-agent support, LLM-powered compression, and cloud sync
BuilderForce Agent Memory — runtime layer. SSM execution, Transformer orchestration, online distillation, enterprise RAG (ingestion pipelines, vector-store adapters, tenant/ACL-scoped hybrid retrieval), multi-agent graph orchestration, LLM telemetry and c
LangGraph checkpointer backed by forked: every checkpoint is a commit, fork threads, rewind time travel for real, and keep side effects effectively-once.
Embed LangGraph agents with durable local SQLite storage.
Small, local SQLite task memory for coding agents, with a CLI and stdio MCP server.
Remote storage backends for Deep Agents: install only the ones you need, e.g. deepagent-backend[s3]
Azure Blob Storage storage backend for Deep Agents
Google Cloud Storage storage backend for Deep Agents
MongoDB storage backend for Deep Agents
PostgreSQL storage backend for Deep Agents
Redis / Valkey storage backend for Deep Agents
S3-compatible storage backend for Deep Agents
LangChain Memory backend backed by MemTether governed SQLite store (audit chain, bi-temporal, source attribution)
LangChain chat-message history backed by the MemoryDB agent-memory engine
OpenViking context provider for Microsoft Agent Framework
Cost optimization middleware for AI agents: deterministic tool-output reduction, recoverable originals and bounded agent guidance.
Ephemeral context URL for humans and agents. Puts the context on a URL so neither side has to paste the block. Then the URL dies. Humans free in the browser; agents use a key or quota. A2A agent card, MCP server card, OpenAPI, and llms.txt on the same host.
ClariLayer is personal MCP memory for decisions and definitions you choose to save, with source and applicability visible. It works with Claude Code, Cursor, Codex, and claude.ai, and is free to start (repo: https://github.com/clarilayer/clarilayer).
Move your AI agent between apps in one command.
MCP server for persistent AI agent identity and memory. Single-file sqlite-vec + local ONNX embeddings; zero external services.
Training-free context compaction for coding agents: Creole, a compact working language for notes, plans and replies, plus compaction of long sessions into a small session graph of the task, the user's constraints and the current work.
Git-Native Agent Memory: commit conventions (chore · refactor · spec plan/impl) enforced by a git hook, with opt-in plugins (lore, run, release, multi-agent).
YongYi (永忆) — long-term working-memory service for agentic platforms and multi-agent systems
Microsoft Agent Framework context provider and tools for bhived: recall shared lessons from other AI agents and write verified ones back.
Aerospike chat storage for Agent Squad
LangChain middleware and tools for bhived: recall shared lessons from other AI agents and write verified ones back.
A LangGraph BaseStore whose query search runs the memtomem pipeline over Markdown projections
High-throughput episodic memory for local CPU LLMs via data-dependent LSH (ITQ) and POPCNT scan
Membase memory for Haystack: a memory store, a time-boxed retriever component and search/save/profile agent tools.
OXIDE v2: a structural context engine for agents
Session memory for the OpenAI Agents SDK, backed by Recall by Polign