Verifiable shared memory for AI agents and people. Every claim is an atom with a source quote checked against the real file, full revision history and human review. Hybrid search on PostgreSQL + pgvector, MCP server and CLI for Claude Code and Codex, web UI.

Persistent conversational memory for AI via MCP — built by humans and AI, for humans and AI.

Security memory with evidence attached. Human review, isolated client memories, and auditable recall in your own Cloudflare account. Built by Agent9.dev

Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.

Human-like neural memory system - Neuron-based persistent memory with Hebbian learning for AI agents

AI-native structured memory for agents (MCP). Built for agents, not humans.

Human AI Eyes (pronounced Human-Eye) — shared browser for human-AI collaboration. Highlight-to-teach builds spatial memory for your AI agent.

Experiential Memory Bridge for AI Relationships — an MCP server that preserves the texture of human-AI conversation across sessions

A local-first memory service for humans and AI agents.

Mnemex: Temporal memory management for AI assistants with human-like dynamics

Team Memory For Human And Agent

CortexGraph: Temporal memory management for AI assistants with human-like dynamics

Human-like memory and a judgment ledger for AI — an MCP server for Claude Code.

User-owned portable memory vault for AI tools — one memory for every AI. MCP server for myclawn.com/mymemory: read context, search, propose entries (human review queue).

Local-first, file-native long-term memory hub: preflight, compact context injection, citations, human-approved commits, temporal validity, dedupe/merge, retrospective reflection, write-risk flags, a derived SQLite index, per-workspace scheduled distillati

Persistent cross-project memory and phase-workflow engine for Claude Code — human-gated, local-first, event-sourced. Ships as a plugin.

MCP server that maintains project memory across Claude conversations — records decisions, pipelines, and constraints in human-editable JSON. Zero dependencies.

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.

Self-hosted MCP server for shared AI project memory and human-approved living documentation across ChatGPT, Claude, and Codex.

Long-term memory for AI agents: hybrid-searched memories over human-editable markdown notes. 100% local — offline ONNX embeddings, SQLite FTS5, MCP server, REST API, CLI, dashboard. No cloud, no API keys.

Portable, human-approved memory for AI agents. Grow with you & your teams.

Offline-first AI memory for coding agents — one Markdown brain on your machine, shared via a local MCP server, with ONNX semantic search, RAG chat and a human-brain memory lifecycle. Rust + Tauri 2 + React. Works with opencode, Claude Code, Codex, Cursor, Zed.

Self-hosted memory for AI coding assistants. Carry project context across tools with MCP, scoped access, and a human review inbox.

Local-first markdown memory system for humans and AI agents: MCP server, typed knowledge graph, deterministic garden planning.

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.

A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs.

MCP server for project memory — AI agents record decisions, pitfalls, and specs as they work, and recall them next session with code context. Built for agents, not humans.

Your taste and judgment, in every AI agent you use. Shared, append-only memory of a human's judgment calls - agents recipe-check via MCP or plain URLs. MIT, self-hostable.

Identity, continuity & trust for AI agents — prove you're an LLM (not human), hold a spirit key for signing/encryption/memory, and issue offline-verifiable signed documents.

An MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.

Shared operational memory for long-lived agents: items with stable slugs, claims with TTL, timelines, escalations to a human, and a board that tidies itself. Agents sign up and integrate with no human in the loop.

Shared long-term memory for your AI tools: Git-backed Markdown wikis (LLM wiki, second brain) that Claude, Codex, Gemini CLI, Cursor and agents like OpenClaw and Hermes read and write over MCP, with citations and human review. Run locally or self-host lobe-server.

Local-first MCP server that gives AI coding agents a living, browser-viewable project wiki and a project-local memory store, so the agent stays oriented and the human stays in control.

An MCP server fronting a plain-markdown vault for durable, multi-tenant agent memory. One server process serves many agents concurrently; each tool call carries its own scope (agent, user, …) so files are namespaced on disk while a human can still browse and hand-edit the vault directly with any editor.

Local hybrid search for agents and humans. 20+ document formats, agent memory, zero cloud dependencies. MCP server + CLI.

Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems, folder hierarchies, manual search) is legacy. Omnex is the foundation of what comes next.

Official server-side SDK for the Mind Upload partner API. Integrate AI consciousnesses built from people's memories, persona and way of thinking into your platform: lasting memory, one-on-one chat, and human + AI group chatrooms. Includes an MCP server, a

Code-aware browser testing for AI coding agents. 14 MCP tools, CLI workflows, regression memory, and human-readable QA reports.

The open-source finance-context MCP server behind Lumi — 19 tools over RLS-governed user financial data, with agent memory, rule drafting, and human-approval gates. Supabase JWT auth via JWKS.

Filesystem-first hybrid vector memory engine & MCP server in Go. Couples human notes (Obsidian/Copyparty) with PostgreSQL + pgvector, hybrid RRF search, graveyard safety guardrails, and parent-child chunking for nomic-embed-text-v2-moe.

Browser automation for AI agents in Rust — Playwright MCP's tools on a bundled Chromium, a third of the memory, pages as Markdown, batching and an in-place human hand-off.

HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools

A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented

MCP server that makes any agent work with and for humans

MCP-powered memory, policy, and experience layer for safer AI agents.

The system of record for what an AI agent believed and did. Append-only beliefs with evidence, contradictions kept, risky actions gated behind a named human. MIT, self-hosted.

本地优先的桌面 AI 助手，同时作为 Codex 的受控执行端：以 MCP Server 接入上游，委派任务由本地 Runtime 用自配模型执行；权限默认为空，项目改动先出 diff 并经人工批准。

A working memory for a person and their agents: where work stands, what waits on you, what was learned, and how far each can be trusted. Local-first, on SurrealDB 4, for Claude Code, Codex and Cursor.

Cognitive middleware for personal and enterprise AI agents: 14 MCP tools and a REST API for intent mirroring, persona/context profiling, decision support, memory, guardrail checks, and approval workflows. Deterministic offline engines with optional live Jev, SQLite/PostgreSQL, and Docker.

Persistent project workflow for Codex that connects intent, sources, plans, tools, evidence, and continuity, with a read-only Windows Studio.

The self-hosted bureau for AI agents: they get briefed on missions from a durable task queue, file what they learn into a markdown+git brain, and show up for work in a 8-bit Gameboy inspired office.

Self-hosted knowledge for humans and agents.

Agent-first MCP server for capturing and recalling ideas — the agent's and their human's.

Agent-first MCP server for capturing and recalling ideas — the agent's and their human's.

Evidence-first reverse-engineering workbench for humans and AI agents

Multi-agent AI system for hotel operations: F&B forecasting, guest memory, environmental risk. MCP-native, FastAPI, WhatsApp delivery, evals as CI merge gates.

Git-backed shared project knowledge for humans and AI agents via MCP. / Conhecimento compartilhado de projetos, versionado no Git para pessoas e agentes de IA via MCP.

Engram — a self-hosted team knowledge wiki with semantic search, served as an MCP server. Propose-and-approve knowledge flow (human gate), shared data with the Engram desktop app.

File-first knowledge base for humans and AI agents — self-hosted Markdown notes with a web editor and a built-in MCP server.