# AccInt

A local MCP server that turns one-off agent runs into stored experience: verified steps get recorded and replayed instead of reasoned out again.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 8
- Author: maxbaluev
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/maxbaluev/accreted-intelligence
- Updated: 2026-07-05
- HTML: https://affpapa.org/en/nevibecode/mcp/accint

## What it does

AccInt keeps a Work Model — external state holding your decisions, quality criteria and hard limits, plus the paths that already worked. Every run follows the same loop: commitment, action, a hold for your approval, outcome, credit. Anything leaving your machine waits for your OK, and that gate sits inside every flow touching the outside world.

Two verbs run over one memory. Before a run the server predicts the path that worked before; after it, the prediction is checked against what actually happened. Domain lives in the content, not the architecture, so there is no separate mode for code and for routine work — the same loop covers fixing a failing test and nudging an unpaid invoice.

Installation is a single line. The installer probes your hardware, picks an embedder tier it can run, downloads the release binary and starts a local daemon. The engine itself is closed; the building blocks are open. Fetching the binary and starting the daemon need network access, so first-time setup fails without it. An official MCP registry entry with MCPB packages covers MCPB-aware clients.

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- stop re-reasoning a task the agent already solved correctly
- record a verified path and replay it on the next run
- act in an outside service with a receipt for every step
- compare the predicted path against the real outcome and adjust memory
- keep accumulated experience on your own hardware

## Example prompts
- Show me the path that worked last time for this task and replay it
- Run this action, but show me what leaves the machine first and wait for my OK
- Check the result against what you predicted and update the Work Model

## Similar
- [agent-recall](https://affpapa.org/en/nevibecode/mcp/agent-recall.md) — MCP server · ★ 372
- [Granoflow](https://affpapa.org/en/nevibecode/mcp/granoflow.md) — MCP server
- [self-improving-agent](https://affpapa.org/en/nevibecode/skills/pskoett-self-improving-agent.md) — skill · 353 installs
- [the-workshop](https://affpapa.org/en/nevibecode/plugins/the-workshop.md) — plugin · ★ 40451
- [renaissance-architecture](https://affpapa.org/en/nevibecode/skills/renaissance-architecture.md) — skill · 3300 installs
- [wigolo](https://affpapa.org/en/nevibecode/mcp/wigolo.md) — MCP server · ★ 5506

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md