hypotree
Active·★ 12·MIT·Updated 2026-08-20
Hypotree structures an agent's working knowledge as a persistent, self-revising hypothesis DAG, exposed as an MCP server and a Python API. It revises beliefs, prunes dead branches and deduces survivors by elimination, instead of just accumulating facts like a vector store.
#agentic-memory#agentic-memory-architecture#ai-agents#dag#graph-memory#hypothesis#hypothesis-testing#mcp
01
Features
01Write-back belief revision that propagates evidence failures upstream
02Cascading prune of a refuted hypothesis and its subtree
03Exclusion-group inference and deduction by elimination
04Thompson Sampling navigation of the open frontier
02
Compatibility
Claude Desktop
Client
Verified via docs
Cursor
IDE / Editor
Verified via docs
Cline
Extension
Verified via docs
Python
Runtime
Verified via docs
Node.js
Runtime
Verified via docs
macOS
OS
Verified via docs
03
Quick start
1
$ pip install hypotree
04
Use cases
↳Track hypotheses in agentic research and development without wasting tokens on dead ends
↳Maintain a belief state that revises itself as evidence changes
05
Alternatives
altium-designer-mcp★ 82
MCP server for AI-assisted Altium Designer component libraries management
comfy-skills★ 233
Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for the installer and MCP server.
agent-device★ 5.1k
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
ruvos★ 28
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persistent memory, resumable signed sessions, multi-agent orchestration, a knowledge graph, safety guardrails, and a signed audit trail. Zero Node.js, zero SQLite, zero daemon.
openislands★ 21
Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.
ar★ 20
Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.
Comments
Log in to leave a comment
No comments yet. Be the first!