§ 01 · OPEN SOURCE · MIT LICENSE · EARLY SCOUT RELEASE

Run AI Agents as One Go Binary.

Gormes is a Go-native runtime for long-running AI agents.

One static binary. No Python runtime. No Hermes process.

Ship the same binary you test. Run it anywhere.

Early-stage and shipping.

Offline TUI, local doctor, provider-backed one-shots, and Goncho memory are ready today.

~22.0 MB static binaryLinux · macOS · WindowsMIT LicenseZero runtime dependencies

INSTALL

Install in one command. Verify everything works.

One command to install from the public repo. Review the script first, then run it.

1. INSTALL

curl -fsSL https://raw.githubusercontent.com/TrebuchetDynamics/gormes-agent/main/scripts/install.sh | sh

2. OFFLINE TUI

gormes --offline

3. LOCAL DOCTOR

gormes doctor --offline

4. MEMORY AUDIT

gormes goncho doctor --json

5. MODEL-BACKED TURN

GORMES_ENDPOINT="https://your-provider.example/v1" \
GORMES_API_KEY="..." \
GORMES_MODEL="your-model" \
gormes --oneshot "hello from Gormes"

6. BUILD FROM SOURCE

git clone https://github.com/TrebuchetDynamics/gormes-agent.git
cd gormes-agent
make build

The installer clones, builds, and links gormes into your PATH. Or build from source if you prefer. Read the installer source →

See it work in 30 seconds

Build from source, run the offline TUI, and verify your local runtime before touching a model.

curl -fsSL https://raw.githubusercontent.com/TrebuchetDynamics/gormes-agent/main/scripts/install.sh | sh
gormes --offline
gormes doctor --offline
Read the quickstart →

§ 02 · WHY GORMES

Why agent runtimes fail in production

Python-stack agents fail operationally when:

  • dev, staging, and prod stop matching
  • install scripts depend on host package luck
  • long turns die on dropped streams
  • tool wiring fails after tokens are already burning

How Gormes fixes the runtime surface

One Binary To Ship

Zero CGO. ~22.0 MB. The same stripped static binary you test is the artifact you deploy.

No Runtime Drift

No runtime Node or npm, no pip, no env activation. Gormes removes the Python-stack failure class from the shipped runtime.

Recoverable Streams

Route-B reconnect treats SSE drops as recoverable events, so a flaky network does not automatically erase a long turn.

Local Preflight

gormes doctor --offline checks the local runtime surface before a model round-trip. Bad wiring fails before tokens burn.

Transparent Local Memory

gormes goncho doctor --json reports memory DB paths, schema state, queue status, degraded modes, and provider readiness for Goncho.

Release Trust Roadmap

Package-manager manifests, checksums, detached signatures, Windows signing, and AV false-positive submission are explicit release-hardening targets.

Built for operators who ship

  • Static binary you can copy to any server
  • Offline TUI for local development and testing
  • Doctor commands that catch misconfig before tokens burn
  • Goncho memory with transparent local storage
  • Provider-backed one-shots for CI and automation

§ 03 · BUILD STATE

Useful today, still early.

Current focus

  • Offline TUI, local doctor, and provider-backed one-shots
  • Gateway stability and shared channel contracts
  • Goncho memory plus subagent safety

Next milestone

Production-stable Go-native runtime, no Hermes process

View full phase-by-phase checklist
SHIPPED · 4/4

Phase 1 — The Dashboard

  • 1.A Core TUI
  • 1.B Wire Doctor
  • 1.C Automation Reliability
  • 1.D Skill-Driven Control Plane
SHIPPED · 21/21

Phase 2 — The Gateway

  • 2.A Tool Registry
  • 2.B.1 Telegram Scout
  • 2.B.10 WeChat Adapter
  • 2.B.11 Discord Forum Channels
  • 2.B.12 Channel-Neutral Native Runtime Adapter
  • 2.B.2 Gateway Chassis + Discord
  • 2.B.3 Slack on Shared Chassis
  • 2.B.4 WhatsApp Adapter
  • 2.B.5 Session Context + Delivery Routing
  • 2.C Thin Mapping Persistence
  • 2.D Cron / Scheduled Automations
  • 2.E.0 OS-AI Spine: Deterministic Subagent Runtime
  • 2.E.1 OS-AI Spine: Delegation Policy + Child Execution
  • 2.E.2 OS-AI Spine: Concurrent-Tool Cancellation
  • 2.E.3 OS-AI Spine: Durable Job Resilience
  • 2.F.1 Slash Command Registry + Gateway Dispatch
  • 2.F.2 Hook Registry + BOOT.md
  • 2.F.3 Restart / Pairing / Status
  • 2.F.4 Home Channel + Operator Surfaces
  • 2.F.5 Gateway Mid-Run Steering + Active-Turn Policy
  • 2.G OS-AI Spine: Skills Runtime
SHIPPED · 15/15

Phase 3 — The Black Box (Memory)

  • 3.A SQLite + FTS5 Lattice
  • 3.B Ontological Graph + LLM Extractor
  • 3.C Neural Recall + Context Injection
  • 3.D Semantic Fusion + Local Embeddings
  • 3.D.5 Memory Mirror (USER.md sync)
  • 3.E.1 Session Index Mirror
  • 3.E.2 Tool Execution Audit Log
  • 3.E.3 Transcript Export Command
  • 3.E.4 Extraction State Visibility
  • 3.E.5 Insights Audit Log
  • 3.E.6 Memory Decay
  • 3.E.7 Cross-Chat Synthesis
  • 3.E.8 Session Lineage + Cross-Source Search
  • 3.F Goncho Honcho Memory Parity
  • 3.G Goncho Drop-In Compatibility Closure
IN PROGRESS · 7/13

Phase 4 — The Brain Transplant

  • 4.A Provider Adapters
  • 4.B Context Engine + Compression
  • 4.C Native Prompt Builder
  • 4.D Smart Model Routing
  • 4.E Trajectory + Insights
  • 4.F Title Generation
  • 4.G Credentials + OAuth
  • 4.H Rate / Retry / Caching
  • 4.I Native Agent Turn Closure
  • 4.J Permission-Hardened Tool Execution
  • 4.K Provider Fallback Chain
  • 4.L Safety-Anchored Turn Loop (MOSAIC)
  • 4.M Advanced Provider Routing
IN PROGRESS · 5/22

Phase 5 — The Final Purge

  • 5.A Tool Surface Port
  • 5.B Sandboxing Backends
  • 5.C Browser Automation
  • 5.D Vision + Image Generation
  • 5.E TTS / Voice / Transcription
  • 5.F Skills System (Remaining)
  • 5.G MCP Integration
  • 5.H ACP Integration
  • 5.I Plugins Architecture
  • 5.J Approval / Security Guards
  • 5.K Code Execution
  • 5.L File Ops + Patches
  • 5.M Mixture of Agents
  • 5.N Misc Operator Tools
  • 5.O Hermes CLI Parity
  • 5.P Docker / Packaging
  • 5.Q API Server + TUI Gateway Streaming
  • 5.R Code Execution Mode Policy
  • 5.S Loop Detection
  • 5.T Browser Harness Doctor
  • 5.U Fault-Tolerant Sandbox Execution
  • 5.V Unified Event Bus
IN PROGRESS · 6/12

Phase 6 — The Learning Loop (Soul)

  • 6.A Complexity Detector
  • 6.B Skill Extractor
  • 6.C Skill Storage Format
  • 6.D Skill Retrieval + Matching
  • 6.E Feedback Loop
  • 6.F Skill Surface
  • 6.G Structured Memory Types
  • 6.H Skill Metadata Placement
  • 6.I Zero-LLM Knowledge Graph
  • 6.J Agentic Memory Lifecycle (AgeMem)
  • 6.K Self-Evolution Engine (GEPA)
  • 6.L Composable Skill Execution (Voyager)
IN PROGRESS · 2/5

Phase 7 — Paused Channel Backlog

  • 7.A Signal Adapter
  • 7.B Email + SMS Adapters
  • 7.C Matrix + Mattermost Adapters
  • 7.D Webhook + Trigger Ingress
  • 7.E Regional + Device Adapter Backlog

Ready to try Gormes?

Build from source in under a minute. No Python runtime. No Hermes process. One static binary.