# hypotree

> hypotree — tygryso-hypotree. Use this tool when you need to manage complex hypotheses and revise beliefs based on evidence, enabling agents to structure knowledge as a directed acyclic graph with automatic updates and pruning. It solves problems of knowledge management, belief revision, and hypothesis testing in agentic R&D. The hypotree tool takes in hypotheses and evidence as inputs and outputs a revised graph of working knowledge, ideal for use in research and development contexts where knowledge is constantly evolving.

Canonical page: https://skillsregistry.net/skills/tygryso-hypotree  
JSON: https://api.skillsregistry.net/v1/skills/tygryso-hypotree

## Description

A persistent, self-revising hypothesis DAG for agentic R&D, exposed as an MCP server. It enables agents to structure working knowledge as a directed acyclic graph of hypotheses, with automatic write-back belief revision and cascading pruning based on evidence.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hm04k914lg)
- **Repository:** <https://github.com/tygryso/hypotree>

## 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": "tygryso-hypotree"
    }
  }
}
```

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