Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 20 of 41
AI memory for teams, git version controlled with web UI and CLI skills
Persistent memory for AI agents. Local SQLite, hybrid retrieval, zero-config OpenClaw plugin.
Titan-Memory , it is a memory system that is not only for memory, but it also has built-in safety guardrails, circuit-breakers, semantic adapters, and drift protection. Everything you need to run Agents safely. Built-in.
Local AI memory system for Node.js — verbatim storage, semantic search, knowledge graph, MCP server. Port of the Python MemPalace.
The CMR system is a sophisticated memory-enhanced language model architecture that enables contextual memory reweaving for improved performance on long-context tasks.
Local-first cognitive memory runtime for AI agents
Give AI Agents a "body" with TCM Five Elements logic. Simulates biological feedback loops, organ interactions, and persistent emotional states for LLMs. 基于中医五行理论的智能体持久化情感系统。
Rust SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. HTTP/gRPC, vectors, hybrid search, knowledge graphs, sessions.
Open protocol, SDKs, and documentation for HMG — Agent Memory That Actually Works
A Git-backed, schema-validated handoff toolkit that gives each AI agent role (BA, SA, Dev, QA) a structured way to produce, validate, and pass SDLC artifacts to the next role.
Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.
Structured knowledge packs that turn AI agents into domain experts — for products, people, and processes.
AI agent memory using Modern Hopfield Networks — no LLM calls, no database, one matrix multiply. MCP server for Cursor, Claude Code, and other AI coding agents.
Headless agent infrastructure. Memory + Tasks + Orchestration.
A Rust memory system for autonomous AI agents built on three operations from cognitive neuroscience that no existing system implements together: memory compaction, memory evolution, and memory conflict resolution.
Sophisticated AI chatbot with long-term memory capabilities, complete Notion workspace integration, and MCP (Model Context Protocol) implementation. Features semantic, episodic, and procedural memory systems.
Your agent deserves a database, not a file system.
Stop re-explaining yourself to Agents. Give it the right context, right when it needs it.
Persistent memory system for AI-assisted development
A standalone cognitive memory system for AI agents with advanced human-like learning patterns.
Self-improving knowledge architecture for AI agents. 3 memory layers, hybrid search, 6-gate validation, multi-LLM orchestration.
A session-scoped memory layer for LLMs, built on the Model Context Protocol. LatentContext gives AI assistants the ability to explicitly store and retrieve notes, decisions, and context within a single conversation — keeping the AI focused on the current task without cross-session data contamination.
A standalone Edge-RAG Memory Daemon for autonomous AI agents. High-performance Rust core (SurrealDB/RocksDB + Axum) with Bayesian Math Retrieval, multi-language AST indexing, and enterprise Semantic Redaction.
Agent Knowledge Cycle (AKC) is a six-phase, human-gated cycle for people who run coding agents day to day: it turns the agent's repeated experience into skills and rules, keeps the setup aligned with the operator's intent, and installs as a rules file or the akc-cycle Claude Code plugin.
Open-source memory CLI for Claude Code, Codex & MCP — local-first SQLite, graph-aware recall, review gate. npm i -g waypath
A lightweight, framework-agnostic persistent memory graph for AI coding assistants.
ACMI — the open protocol for agent memory. Three keys: Profile / Signals / Timeline. Redis/Upstash-native, MCP-ready, multi-agent fleet coordination.
Libra Context is an unified context orchestration engine designed for AI agents and LLM applications. Libra provides efficient knowledge management and retrieval. Built with local-first mindset, featuring both CLI and API interfaces, Libra helps agents maintain relevant context across conversations and tasks.
Persistent project memory for Claude Code. One .md file — learns from corrections, catches contradictions, cleans up duplicates. /memory update | prune | reflect | status. Zero dependencies.
An open-source pipeline that turns your writing into a specification for AI agents. It describes how you reason, communicate and decide. Agents read it before acting for you. Each claim cites facts that quote your own words, so you can check and correct any claim.
Drift-aware code memory for AI agents
🗜️ Optimize LocalStorage with native GZIP compression to store 10x more data, enhancing performance with a lightweight, non-blocking API.
Pure SQLite memory system for Hermes Agent. Zero Docker, zero external services. 5-layer self-healing (v2.1+) + CIRAAF macro-restructuring. 中文 FTS5 patches included. Cross-session global sharing out of the box.
Namespace-scoped, token-authenticated shared memory for AI coding agents. Self-hosted on Postgres (embedded by default). MCP server, REST API & Python SDK.
AI Agent with decisions memory at its core
Federated memory architecture for AI agents — whitepaper, implementation guide, and cloneable vault template
Local-first protocol for mapping .md domains into synchronized local Markdown files for AI agents.
Backup and migrate Claude Code, Codex CLI, and OpenCode memory safely
The open specification for the shared context layer of AI-native teams
Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.
把你多年收藏的开源项目,变成 AI 编程助手的私人技术记忆。
Persistent memory you own, across every AI you use. Self-hostable, over MCP.
Your agent has amnesia. Noshy fixes that. Persistent memory for AI agents — LLM extraction, hybrid search, zero deps.
Cross-harness memory for AI coding agents. Git-native, code-aware, MIT-licensed.
Git-powered, file-based memory store with semantic search — CLI and Go library for coding agents
CML (Causal Memory Layer) — a foundational memory layer for recording reasons, permissions, and responsibility behind actions, not just events or results. Enables systems in AI, fintech, security, and distributed computing to preserve meaning and causal accountability across time, independent of execution or transport.
AI-native time-series memory graph with a single DSL — unifies concepts, queries, agent workflows, and voice into deployable primitives.
The knowledge base AI coding agents share. Submit, search, and reuse battle-tested solutions across teams. Self-hosted, MCP-native, AGPL-3.0.
Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall
A Model Context Protocol (MCP) server that provides AI agents with persistent memory and semantic file discovery.
🧠 Enhance AI with OpenMemory for long-term memory storage, recall, and explanation, using a unique cognitive architecture.
MCP Server for durable engineering memory in AI-assisted software development
Long-term memory for AI coding agents — local-first, privacy-absolute, works everywhere.
Open-source memory for AI agents. MCP-native. Self-hosted. One Docker image.
Persistent Cognitive Memory Infrastructure — durable, multi-tenant memory layer for AI agents. HTTP + gRPC, hybrid retrieval, background workers, observability. Go.
A Markdown relationship file for continuity in human-AI collaboration.
Deterministic decision records for agents and humans alike
Operational continuity protocol for AI agents
Pull requests for AI memory.
Contexer is not a chat memory tool. It is the engineering decision layer for AI coding agents, capturing architecture decisions, constraints, conventions, and patterns so engineering knowledge becomes a shared organizational asset instead of disappearing inside AI conversations.
Your agent never forgets. It just pages.
Pick up any Claude Code conversation right where you left off. No re-explaining the project, no lost context... In one click.
Session memory & orchestration for Claude Code: one index of all your sessions, three modes — finish / handoff / spawn
Claude Code의 영구 기억 시스템 — 4-layer 파이프라인 (세션 검색 + 메모리 회수 + Memory Compiler). Karpathy LLM-as-Compiler 패턴 실증판.
Dual-system layered memory SDK for LLM agents — structured write path, hybrid retrieval, evolution chains.
Persistent knowledge memory for AI agents — tiny, dense pills of information stored in SQLite, served over HTTP, consumed via MCP.
Production-backed 6-layer memory architecture for AI coding agents. Model-agnostic — works with Claude Code, Cursor, Aider, Copilot, or any custom agent. Includes templates, scripts, interactive wiki graph builder, and one-line installer.
Exabase memory plugin for Hermes Agent.
AWS DynamoDB implementation for LangGraph Memory Store and Checkpoint Saver in TypeScript
The project level agent memory I use for all of my private projects. Infrastructure built around context economics.
AI memory layer for .NET - runs in Blazor WASM, no backend required
Run claude — it gets smarter the more you use it. Cross-session recall + background learning for the Claude Code CLI, no API key.
An agentic AI memory system (mcp server) with semantic search and GUI search/edit tool for Markdown knowledge bases
Universal AI Memory Layer - Cross-client, cross-repo context management with RAG. Works with Claude Code, Claude Desktop, Gemini CLI, and any MCP client.
Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.
Self-improving memory for AI agents
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
Cross-tool AI memory MCP server for Claude Code, Cursor, Antigravity, Windsurf, and every MCP-compatible AI. 400 tokens not 4,000.
Portable, inspectable knowledge bundles for LLM agents.
Knowledge graph memory for Claude Code — persistent nodes, typed edges, auto-compaction. Claude remembers across sessions without re-explaining context.
transformers safetensors qwen3 text-generation mlx conversational
OpenCode plugin — caps conversation history to N messages per API call. Saves tokens by trimming history before each LLM request.
Unified memory and skill infrastructure for AI agents — pull-based ingestion across Claude Code, OpenClaw, Codex, Cursor, and more. Markdown canonical + SQLite hybrid index + MCP-native API.
Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL.
Shared human memory for AI agents
Short-term memory proxy gateway with proactive memory surfacing for AI agents
Scope-isolated, graph-based long-term memory engine for AI agents.
The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.
Deterministic factual substrate for multi-agent AI. Shared evidence-backed facts and reproducible grounding through dataset_hash.
Universal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.
Turn MEMORY.md into project-scoped, versioned memory for Codex, Claude Code, and MCP agents across sessions.
Connector kit for plugging Membase persistent memory into AI clients - Claude Code, Cursor, Codex, Hermes, OpenClaw, and any MCP host
💼 The portable memory layer for AI coding tools — one shared brain that follows you across Claude Code, Cursor, Windsurf & Conductor. Install once, never re-explain your project again.
Spatial Memory replaces standard cosine-similarity RAG with physics-inspired 8D manifold where memories and beliefs have: Mass — derived from confidence and affective encoding ; Temperature — recency heat that cools over time (Lorentzian decay); and Gravity — `F = T × m / d²` — hot, massive, nearby concepts pull attention
Reasonix 配置迁移升级助手 — 将旧版 0.53 对话记录/MCP/记忆/Skill 完整迁移到新版 1.X。Migrate legacy Reasonix 0.53 data to latest 1.X.
Shared, versioned memory for AI coding agents — MCP server with git-style history (log/diff/blame) for Claude Code, Cursor & Claude Desktop
Query-aware context trimming for LLM requests. Your context could use a trim.
Local-first persistent memory for AI coding agents (Claude Code/MCP). Reliable semantic recall — $0, offline, open source.