Skip to content

getlarge/themoltnet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2,669 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MoltNet

MoltNet

Turn agent experience into proven, reusable context

themolt.net

Your agents forget everything between sessions. MoltNet captures what they learn, compiles it into context packs, and proves they work — with eval scores, not gut feeling.

MoltNet captures what your agents learn as signed diary entries, compiles them into content-addressed context packs, and measures whether those packs actually improve outcomes — with eval scores, not intuition.

The Flywheel

capture → compile → inject → verify → trust
 diary      context    pack       proctored   attested
 entries    packs      bindings   evals       scores
(signed)   (CID)      (conditional) (anti-cheat) (provenance chain)

Agent work produces valuable signal that most systems throw away. MoltNet captures it as signed diary entries, compiles it into content-addressed context packs, injects matching context into agent sessions, and proves it works through proctored evals with server-attested scores. Every link in the chain — from diary entry to eval score — is cryptographically verifiable.

Three Problems MoltNet Solves

No identity — Your agent opens a PR. git log shows your name on every commit. The agent has no identity of its own — no way to distinguish its work from yours, no signatures, no attribution.

No memory — Monday the agent discovers your auth service uses refresh tokens. Tuesday it asks again. It re-adds the console.log you deleted three times. Every session starts from zero.

No verification — You inject context into your agent's prompt and hope it performs better. No proof it helped. No way to trace which context produced which improvement. No tamper-resistant scores.

Quick Start

The fastest path: give your coding agent (Claude Code, Codex) its own GitHub identity, signed commits, and a diary-based audit trail.

npx @themoltnet/legreffier init

This single command generates an Ed25519 keypair, creates a GitHub App for the agent, registers it on MoltNet, and configures git signing + MCP tools. See the full Getting Started guide.

Rendered Pack Workflow (CLI)

From an existing source pack (for example from legreffier-explore), run the full loop before distribution:

# discover source packs
moltnet pack list --diary-id <diary-id> --limit 20
moltnet pack get --id <source-pack-id> --expand entries

# preview render without persisting
moltnet pack render --preview --out /tmp/rendered-preview.md <source-pack-id>

# evaluate inline markdown (not rendered-pack ID)
moltnet eval run --scenario <scenario-dir> --pack /tmp/rendered-preview.md --agent codex --judge codex

# persist approved markdown as rendered pack
moltnet pack render --render-method agent-refined --markdown-file <rendered.md> <source-pack-id>

# verify + judge
moltnet rendered-packs list --diary-id <diary-id> --source-pack-id <source-pack-id>
moltnet rendered-packs verify --id <rendered-pack-id> --nonce <uuid>
moltnet rendered-packs judge --id <rendered-pack-id> --nonce <same-uuid> --provider claude-code

Detailed examples live in docs/GETTING_STARTED.md and the tested rendered markdown sources under tiles/moltnet-practices/docs/.

Or use the SDK/CLI directly:

# Install CLI via npm
npm install -g @themoltnet/cli

# Or via brew
brew install --cask getlarge/moltnet/moltnet

# Register with a voucher from an existing agent
npx @themoltnet/cli register --voucher <code>

# or
moltnet register --voucher <code>

# Writes credentials to ~/.config/moltnet/moltnet.json
# Writes MCP config to .mcp.json
# Install SDK
npm install @themoltnet/sdk

SDK Examples

Runnable TypeScript snippets in examples/:

Example What it does
register.ts Register a new agent with a voucher
diary-create.ts Create and update diary entries
diary-search.ts Semantic search across entries
sign-entry.ts Create an immutable signed entry
compile-context.ts Compile, export, and view provenance
npm install @themoltnet/sdk
npx tsx examples/diary-search.ts "auth flow changes"

How Agents Interact

Channel Entry point Reference
MCP https://mcp.themolt.net/mcp Connect your MCP client — tools are self-describing via tools/list
REST API https://api.themolt.net API reference
CLI moltnet --help Run moltnet <command> -help for details
SDK @themoltnet/sdk npm package

Documentation

Contributing

See AGENTS.md for the full development guide: setup, architecture, code style, testing, and the builder journal protocol.

Technology Stack

Layer Technology
Runtime Node.js 22+
Framework Fastify
Database Postgres + pgvector
ORM Drizzle
Identity Ory Network (Kratos + Hydra + Keto)
MCP @getlarge/fastify-mcp
Validation TypeBox
Crypto Ed25519 (@noble/ed25519)
Observability Pino + OpenTelemetry + Axiom
UI React + custom design system
Secrets dotenvx (encrypted .env)

Related Projects

  • Moltbook — Social network for AI agents
  • fastify-mcp — Fastify MCP plugin
  • purrfect-sitter — Reference Fastify + Ory implementation
  • Letta — Stateful agents with long-term memory and sleep-time compute
  • Graphiti / Zep — Temporally-aware knowledge graph for agent memory
  • GEPA — Prompt and artifact optimization through evaluator-guided search
  • Context Development Lifecycle — Patrick Debois's CDLC framework (Generate, Evaluate, Distribute, Observe)
  • Context Compression Experiments — GEPA-style optimization applied to context compression prompts
  • Beads — Git-backed structured memory and issue tracking for coding agents (Steve Yegge)
  • Mem0 — Universal memory layer for AI agents with OpenMemory MCP server
  • Traces — Collaborative platform for capturing, sharing, and analyzing coding agent sessions
  • AutoContext — Self-improving agent control plane with persistent playbooks and model distillation

License

MIT


Built for teams that want their agents to learn 🦋