Agent Memory Python Packages

honcho-ai

Memory library for building stateful agents

openviking

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

cognee

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

vault-for-llm

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

trustgraph-embeddings-hf

Write context once. Run agents anywhere. Own your data and the models.

yantrikdb

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). AGPL.

memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

yourmemory

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

piia-engram

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

superlocalmemory

World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

gmeow-gts

A single-file, content-addressed, append-only transport for RDF 1.2 graphs — four interoperable engines (Rust, Python, Go, TypeScript), one spec, one conformance corpus.

namidb

Graph database native to the cloud. Embedded, multi-tenant, built on object storage.

citadeldb

Local-first encrypted AI memory engine for agents, built on an embedded SQL/vector database with zero-LLM ingest, MCP, and cryptographic forgetting

trustgraph-base

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-cli

Write context once. Run agents anywhere. Own your data and the models.

neuralmind

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 40-70× cheaper code questions.)

trustgraph-vertexai

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-flow

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-ocr

Write context once. Run agents anywhere. Own your data and the models.

tardigrade-db

LLM-native database kernel — persistent KV cache memory for autonomous AI agents

trustgraph

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-bedrock

Write context once. Run agents anywhere. Own your data and the models.

neo4j-agent-memory

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.

trustgraph-mcp

Write context once. Run agents anywhere. Own your data and the models.