io.github.Medhovarsh/forkmind
medhovarsh.github.io
Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.
Description
ForkMind 🧠 · Treat AI context windows like a Git repo: capture, branch, and regression-test LLM calls as a DAG — and offload context into encrypted, restorable capsules instead of truncating it. Free & local via Ollama, any OpenAI-compatible API, and MCP for agents. · What it does · Quick start
Installation
npm:forkmind
Not sure where to start — ask an assistant to walk you through:
Specs
| Type | MCP server |
| Section | MCP servers |
| Pricing | free |
| Platform | Command line |
| Systems | cli, api |
| Hosting | local |
| Install | mcp |
| Protocols | mcp |
| Site language | en |
| GitHub | Medhovarsh/forkmind |
| Launched | 2026-07-18 |
Can do
Protocols
Tags
agents
api
workflow-automation
Ollama
mcp
Model Context Protocol
AI agent memory
llm observability
llm debugging
local-first
context capsules
OpenAI proxy
encrypted context storage
AI agent debugging
conversation DAG
regression testing LLM
LLM context management
context window offloading
prompt engineering tool
