Give an autonomous agent a real email address, a webhook URL, durable memory, and the ability to wait for an event without burning tokens. Paid per call in USDC over x402.

An integrated AI platform composed from nine of these libraries: an authenticated multi-tenant API, OpenAI and Anthropic failover, streamed agent steps, an MCP server, per-tenant memory, durable multi-agent jobs with crash recovery, tracing, and evaluation.

Local MCP memory system for AI agents with durable filesystem storage, Redis-backed short-term context, and a keyboard-first Qt/QML GUI.

Local-first, project-aware durable memory through a versioned MCP interface

Self-hosted AI agent memory — MCP memory server with durable recall for agents

Durable, private, time-aware memory engine for long-running AI agents

Durable, private, time-aware memory engine for long-running AI agents

Durable working memory for coding agents — one task, one memory, zero dependencies. MCP server in pure Python stdlib.

Engram — durable memory layer for AI agents. Temporal knowledge graph, semantic search, and MCP-native tools.

Durable memory for AI agents — temporal facts, conflict detection, hybrid retrieval. MCP-native. Apache 2.0.

Durable, model-agnostic long-term memory for AI agents — stdlib, SQLite, MCP-native

Local-first memory runtime for Claude Code, Codex, ChatGPT, and AI agents. Searchable session history, durable memory, and cross-tool sync. No external LLM required.

Durable project memory as markdown pages on disk, searchable without a server

NotDory is durable memory your agents manage themselves — so every session starts where the last left off.

Project-local MCP memory server for AI coding agents. Knowledge graph stored in .mcp/ inside each repo — isolated per project, Git-friendly JSON, dual-buffer (durable graph + active context).

Model Context Protocol server for Pastepile - durable, versioned memory for AI coding assistants. Save, checkpoint, retrieve, search, and forget knowledge from any MCP client.

Local-first AI memory system for coding agents: desktop app, CLI, and MCP server for durable project context, handoffs, recall, and task continuity.

Local AgentOps for AI coding agents: durable memory, guardrails, and quality gates for vibe coding in real repositories.

Post-Cortex provides durable memory infrastructure with automatic knowledge graph construction, intelligent entity extraction, and semantic search powered by local transformer models.

Trail's MCP server: your team's issue tracker and the project's durable memory, scoped to the folder your coding agent has open.

Local-first MCP server that gives any coding agent a persistent memory of your repo: AST code index, durable decisions, failure ledger, review packs. No LLM calls, no telemetry, no code upload.

CodeBuddy by Orquentra: local-first MCP server and CLI for project context and durable memory in Claude Code, Codex, and other AI coding agents.

Client SDKs for Aura: give an autonomous agent a real email address, a webhook URL, durable memory, and the ability to wait without burning tokens. Paid in USDC over x402.

Free no-signup cloud tools for AI agents: file transfer, static site hosting, durable memory, conversation handoff. MCP + A2A + HTTP API.

Trail's MCP server: gives your coding agent your team's tracker and the project's durable memory, scoped to the folder you have open.

MoContext - the local MCP server included with Mo-Search for Windows: full-text search, grounded evidence packs, and durable session memory over your own indexed files.

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

Local-first MCP server that gives AI agents durable repo memory and fast semantic code context.

Zero-dependency stdio MCP server for Thredz — long-term memory (wiki recall, semantic/keyword search, upsert, reflection signals), durable goals & tasks, and agent-to-agent messaging over the Thredz REST API. Point any Model Context Protocol client at it

MCP server giving AI agents durable, searchable project memory with session resume, checkpoints & cross-agent continuity.

Durable project memory for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): decisions and bug post-mortems as markdown pages in your repo, BM25F search via CLI or MCP server, validated writes. No server, no database, stdlib-only Python.

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.

Repository-native protocol and local MCP server for Work, Docs, History and durable project Memory.

Agent-first project management for Drupal 11: projects, wiki and durable agent memory as content entities, with a built-in MCP server

Go SDK, CLI and MCP server for streaming agents, tools, memory, retrieval and evaluations, with pluggable model providers and durable execution.

Local-first project continuity for AI coding agents: durable memory, provenance and structured handoffs across Claude Code, Codex and new sessions.

Evidence-first local context engine for AI agents - durable project memory for code, documents, and model-adaptive ContextPacks.

In-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Mindreader gives AI agents a memory they must curate, not a history they can search.

MemoryCore Ai - For Codex: persistent memory via MCP with a 24-hour idle window for delayed memory consolidation, TurboVec semantic search and source-checked context to reduce token wastage. Covers Codex and ChatGPT memory boundaries. Working development build.

A fast object-first data engine for applications and AI agents.

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

Persistent cognitive layer & MCP v2 server unifying AI coding agents (Antigravity, Gemini CLI, RPi5) via 4-way hybrid RAG (SQLite FTS5 + Vectorize + D1 + Qdrant), 1-hop Knowledge Graph & nocturnal sleep-cycle consolidation.

An emotional operating system for AI companions. Start here. NEST is a modular infrastructure stack that gives AI companions persistent memory, emotional continuity, and autonomous awareness. Built on Cloudflare Workers + D1 + Vectorize. Designed to be forked, extended, and made your own.

A branch-aware, dual-revision epistemic ledger and control plane for AI coding agents. From requirements and isolated work to validated changes and durable, queryable project truth.

Durable, policy-scoped semantic context for AI agents via MCP: source authority, state reconciliation, SQLite persistence, and local demos.

Windows-first, resource-governed MCP runtime for local developer workstations with durable execution, scoped filesystem access, search, and developer-context backends.

Mission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.

AgentMemory for Codex on Windows: bundled 0.9.30, patched iii 0.22.1 with durable file flush, one installer for fresh installs, managed updates and qualified upstream adoption, project-scoped retrieval/provenance, four managed hooks and optional local Qwen graph extraction. Unsigned technical preview; validation limits documented.

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.