Ai Memory Python Packages

honcho-ai

Memory library for building stateful agents

cognee

The memory for your AI Agents in 6 lines of code

keep-skill

Reflective memory for AI agents

memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

mind-mem

v3.7.0 — Persistent, auditable, contradiction-safe memory for coding agents. HTTP/REST auth fail-closed by default. Cross-platform atomic rollback (Linux/macOS/Windows). 71 MCP tools, 17 AI clients, hybrid BM25+vector+RRF, mind-mem:4b (Ollama). LoCoMo 86.33 conv-0 (Mistral, +8.4 vs published).

trw-memory

Persistent memory engine with hybrid retrieval, tiered storage, and semantic dedup for AI agents

mnemo-mcp

Persistent AI memory with hybrid search and embedded sync - open, free, unlimited

velesdb

VelesDB is a local‑first AI data engine written in Rust that unifies vectors, full‑text and graph in a single file with a familiar SQL‑like language. Instead of sending every RAG or semantic search query to a remote cluster, VelesDB runs directly on your server, laptop, browser, mobile or edge device — no cloud dependency, no external services, ..

pensyve

Universal memory runtime for AI agents — framework-agnostic, protocol-native, offline-first

empirica-mcp

Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond

roampal

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

m3-memory

Local-first Agentic Memory Layer Framework for MCP Agents and Multiple Computers • Over 60 tools • Hybrid search (FTS5 + vector + MMR) • GDPR • 100% local

rememb

Persistent memory for AI agents — local, portable, zero config. Works with Cursor, Windsurf, Claude via MCP.

vektori

Memory that remembers the story not just the facts. Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

ogham-mcp

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

nocturnusai

Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get deterministic answers with proof, not LLM guesses. Connect agents via MCP, Python SDK, TypeSc

memorisdk

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

omega-memory

Cross-model memory for AI agents. Local-first, works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client

longhand

Lossless local memory for Claude Code. The full, unabbreviated version. Every tool call, every file edit, every thinking block — stored verbatim on your machine. Persistent memory without tokens.

llama-index-vector-stores-velesdb

VelesDB is a local‑first AI data engine written in Rust that unifies vectors, full‑text and graph in a single file with a familiar SQL‑like language. Instead of sending every RAG or semantic search query to a remote cluster, VelesDB runs directly on your server, laptop, browser, mobile or edge device — no cloud dependency, no external services, ..

langchain-velesdb

VelesDB is a local‑first AI data engine written in Rust that unifies vectors, full‑text and graph in a single file with a familiar SQL‑like language. Instead of sending every RAG or semantic search query to a remote cluster, VelesDB runs directly on your server, laptop, browser, mobile or edge device — no cloud dependency, no external services, ..

nexus-ai-fs

Nexus, the shared heartbeat where every agent and human connect, collaborate, and evolve together.

genesys-memory

Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.

hindsight-hermes

Hindsight: Agent Memory That Learns