EXXETA/exxperts

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

What it solves

Exxperts provides a local-first approach to AI agents that solves the problem of "hidden state" and automatic, ungoverned memory. It allows users to create persistent AI "rooms" where the AI learns and remembers specific information about a user's work, but only after the user explicitly approves the information to be saved.

How it works

The system is organized into "rooms" which act as durable workspaces. Each room can be configured with its own tools, folders, and AI model providers. At the end of a conversation, the AI proposes what is worth remembering; the user then reviews, edits, or rejects these proposals before they are committed to memory. These memories are stored as plain files on the user's local machine, ensuring data privacy and preventing provider lock-in.

Who it’s for

Professionals who want AI assistance with a governed, transparent memory that stays on their own machine, and those who prefer to avoid cloud-based memory systems or provider lock-in.

Highlights

  • Approval-gated memory: Nothing is saved to the AI's long-term memory without explicit user approval.
  • Local-first storage: All conversations, memories, and credentials are stored as plain files on the local disk.
  • Provider agnostic: Works with Claude, ChatGPT, Gemini, Mistral, and local models via OpenAI-compatible endpoints.
  • Auditability: Every memory has a "receipt" (timestamp and source conversation) and the full context behind answers is inspectable.
  • Built-in tools: Includes web search (via DuckDuckGo or SearXNG) and MCP connectors.
  • Multi-interface access: Available as a desktop app, browser-based interface, or CLI.

Related

  • Project
    EverMind-AI/EverOS

    EverOS is a Python library that provides local‑first, Markdown‑backed memory for AI agents. It syncs files to SQLite and LanceDB, offers a simple HTTP API for add/flush/search, and works with a single OpenRouter key for keyword search. Optional extras add embedding‑based hybrid search, reranking, and multimodal file ingestion.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    TencentDB Agent Memory is an open‑source memory hub for LLM agents. It captures conversations, extracts reusable skills, builds a Wiki from docs, and indexes code into a CodeGraph. A central UI (Memory Hub) lets teams manage assets, set fine‑grained ACLs, and bind specific memory pieces to individual agents. Agents talk to a uniform proxy, so any framework (Claude Code, DeepSeek Harness, OpenClaw, etc.) can use the same memory without code changes. Benchmarks show a 59 % boost in persona retention. The repo provides one‑click Docker deployment, migration tools, and a roadmap for zero‑config cold starts and more integrations.

  • Project
    xpert-ai/xpert

    Xpert is an open-source platform and desktop application for orchestrating AI agent teams, providing a governed environment for building, deploying, and managing complex agentic workflows and business applications.

  • Project
    MoizIbnYousaf/ai-agent-skills

    A genuine npm‑based CLI/TUI that ships a curated library of AI‑agent skills, lets you build and manage your own skill collections, and integrates with many LLM‑agents via the Agent Skills spec.

  • Dispatch
    Codex-maxxing: Transforming AI Agents into Durable Operating Loops

    Explore how to move beyond one-off prompts to create long-running, autonomous AI workflows using durable threads, shared memory vaults, and recurring heartbeats.