# knitbrain

> Use this tool when you need to enhance AI coding agents with per-project memory and workflow intelligence, solving problems of context loss and optimization. Knitbrain provides always-on, lossless token and context optimization, taking in AI coding projects as input and outputting optimized workflows. Ideal for use cases requiring persistent memory and intelligent workflow management in AI coding tasks.

Canonical page: https://skillsregistry.net/skills/pdgit12-knitbrain  
JSON: https://api.skillsregistry.net/v1/skills/pdgit12-knitbrain

## Description

Local-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-06-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/s99o10kctv)
- **Repository:** <https://github.com/PDgit12/knitbrain>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "pdgit12-knitbrain"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pdgit12-knitbrain` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pdgit12-knitbrain/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt