A local ForkMind add-on for Claude Code that treats language-model conversations like a version-controlled history. It records calls, supports branches, regression tests, and encrypted context snapshots.

Use it to capture and branch model calls, test for output drift, and offload or restore conversation context through local or compatible model services.

It gives you a way to inspect how prompts and models led to a result instead of losing that history in a chat window.

forkmind — Plugin by Medhovarsh

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add Medhovarsh/forkmind

agentmods

npx agentmods add plugins/medhovarsh/forkmind/marketplace

Clone the repo

git clone --depth 1 https://github.com/Medhovarsh/forkmind

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

forkmind scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 18 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "forkmind",
  "description": "Local-first LLM branching & debugging tool for Claude Code. Treat AI context windows like a Git repo.",
  "owner": {
    "name": "Medhovarsh Bayyapureddi",
    "url": "https://github.com/Medhovarsh"
  },
  "plugins": [
    {
      "name": "forkmind",
      "description": "Capture, branch, and regression-test LLM calls as a DAG — plus context capsules: offload conversation context into encrypted, immutable DAG snapshots and restore on demand. Free & local via Ollama, any OpenAI-compatible API, and MCP for agents.",
      "source": "./",
      "category": "productivity"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

plugin.json 872 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 18 lines scan A f6c1a35f73a8

Subscribe to this mod's changes

forkmind is a plugin published in the GitHub repository Medhovarsh/forkmind (3 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging LLM Memory and context Testing ai-agents dag local-first mcp ollama

gonzo

Set up and use Gonzo, the open-source terminal log analysis tool. Detects deployment platforms (Vercel, Supabase, K8s, Docker, AWS, Cloudflare, Fly, Render, Railway, Netlify), generates the right pipe command with platform-specific normalizers, and configures AI analysis. Use when the user wants to tail, watch, stream.

control-theory/gonzo · not measured

pad

Talk to your project. Pad is local-first project management for developers and AI agents — this plugin gives Claude Code a conversational Pad skill, typed shortcuts (/pad:status, /pad:capture, /pad:onboard, /pad:connect, /pad:disconnect), and consent-gated live item-change notifications.

PerpetualSoftware/pad · not measured

tree-ring-memory

Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.

TerminallyLazy/Tree-Ring-Memory · not measured

cortex

Remembers your decisions, coding conventions, and debugging lessons across every Claude Code session. Persistent local memory for AI coding agents.

AdityaVG13/cortex · not measured

lians

Bitemporal memory for Claude Code with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.

Lians-ai/Lians · not measured

memtrace-skills

Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…

syncable-dev/memtrace-public · not measured