freshcrate

Search results for "agent-memory"

25 results found
mcp-memory-serviceπŸ“v10.39.1🌳 Mature⭐1,643

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

opencode-magic-contextπŸ“dashboard-v0.2.8🌿 Growing⭐124

OpenCode plugin for Magic Context β€” cache-aware infinite context, cross-session memory, and background history compression for AI coding agents

roampal-coreπŸ“v0.5.1🌱 Seedling⭐40

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

rasputin-memoryπŸ“v0.9.1🌱 Seedling⭐17

The memory system your AI agent deserves. 4-stage hybrid retrieval β€” Vector + BM25 + Knowledge Graph + Neural Reranker β€” in <150ms. Self-hosted, $0/query, built for agents that need to actually rememb

mentisdbπŸ“0.9.3.39🌿 Growing⭐56

Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append-only thought chains plus a Git-like skills registry, lett

agentic-memoryπŸ“0.0.0🌿 Growing⭐162

No description

by lhl
MemoriπŸ“v3.3.0🌿 Growing⭐13,290

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

EngramπŸ“v1.0.0🌿 Growing⭐61

Multi-agent memory consistency platform. We're hiring contributorsβ€”check HIRING.md

memsearchπŸ“v0.3.1🌿 Growing⭐1,167

A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.

honchoπŸ“main@2026-04-21🌿 Growing⭐2,030

Memory library for building stateful agents

LycheeMemπŸ“master@2026-04-19🌿 Growing⭐229

Compact, efficient, and extensible long-term memory for LLM agents.

ClawMemπŸ“main@2026-04-19🌿 Growing⭐89

On-device context engine and memory for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.

zvecπŸ“v0.3.1🌿 Growing⭐9,287

A lightweight, lightning-fast, in-process vector database

Awesome-Agent-MemoryπŸ“main@2026-04-16🌿 Growing⭐333

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

prism-mcpπŸ“v9.3.0🌿 Growing⭐116

The Mind Palace for AI Agents β€” Autonomous Cognitive OS with affect-tagged memory (valence engine), token-economic RL (surprisal gate + UBI), Hebbian learning, ACT-R spreading activation, Synapse Engi

skalexπŸ“master@2026-04-20🌱 Seedling⭐15

AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.

memory_agent_hubπŸ“main@2026-04-20🌱 Seedling⭐38

2026 swarm Agent 年,swarm Agent 、Agent team、 ai coding、skill、memory、evolve、agentic RL η­‰ AI Agentι›†εˆ

MemOSπŸ“v2.0.13🌱 Seedling⭐8,264

AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.

memexπŸ“v0.1.27🌱 Seedling⭐79

Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB β€” just markdown + git sync.

membraneπŸ“v0.2.0🌱 Seedling⭐75

A selective learning and memory substrate for agentic systems β€” typed, revisable, decayable memory with competence learning and trust-aware retrieval.

instarπŸ“v0.17.14🌱 Seedling⭐55

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

engram-memory-communityπŸ“main@2026-04-20🌱 Seedling⭐6

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

agent-knowledge-cycleπŸ“v2.0.0🌱 Seedling⭐3

Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.

skill-evolutionπŸ“main@2026-04-21🌱 Seedling⭐2

Enable AI agents to autonomously create, evaluate, and evolve skills across any marketplace without user intervention.