fableforge-agent 0.18.4

FableForge Agent — a fork of Hermes Agent (NousResearch). A self-improving AI agent that creates skills from experience, improves them during use, and runs anywhere

FableForge Agent

A self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere.

Author: KingLabsA

• GitHub: https://github.com/KingLabsA/llm-training-platform
• HuggingFace: https://huggingface.co/King3Djbl | https://huggingface.co/fableforge-ai
• Ollama: https://ollama.com/FableForge-AI

This is a fork of Hermes Agent by Nous Research, rebranded and extended with:

• Agent Control Plane — Sandbox isolation, audit trail with cryptographic signatures, incident response, OAuth gate
• Behavioral Observability — Real-time observation/analysis, semantic firewall, behavior scoring
• Trust Protocols — Ed25519-based handshake/sign/verify, identity registry, permission framework
• Closed-Loop Training — ReMiT mid-train reweighting + RLPT next-segment reasoning RL (via closed-loop-training)

Quickstart

pip install fableforge-agent
fableforge --help

Architecture

┌─────────────────────────────────────────────────────┐
│                   FableForge Agent                     │
├─────────────────────────────────────────────────────┤
│  Agent Core (AIAgent, ConversationLoop, ToolRegistry) │
├──────────┬──────────┬──────────┬──────────────────────┤
│ Control  │ Behavior │  Trust   │ Closed-Loop Training │
│ Plane    │ Observ.  │ Protocols│ (ReMiT + RLPT)       │
├──────────┴──────────┴──────────┴──────────────────────┤
│            80+ Tools, 20+ Platforms, Plugins          │
└──────────────────────────────────────────────────────┘

Built on

Hermes Agent v0.18.x by Nous Research — the foundation that makes this possible.