Skip to content
View landjunge's full-sized avatar
🏠
Working from home
🏠
Working from home
4 followers · 49 following
  • 04:56 (UTC +02:00)

Achievements

Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: YOLO

Block or report landjunge

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
landjunge/README.md

I build open-source infrastructure for controllable AI agents.

Context → Execution → Credentials → Network

AI agents are becoming autonomous. The missing infrastructure is control.

These are separate products — experiments on one problem, not a merged stack.

Layer Project One line
Context ThreadDesk Persistent threads. Stores context. Never executes.
Execution Gnom-Hub-V1 Local multi-agent desk. Brainstorm freely. Execute on purpose.
Credentials 4AllPass Agents need access. They don't need your secrets.
Network / Safety Tollgate Safety layer between agents and the internet. Protect · Route · Prove. 
ThreadDesk      context / work / threads
     ↓
Gnom-Hub-V1     execution
     ↓
4AllPass        credentials  “May I access?”
     ↓
Tollgate        network / cost / safety  “May I act?”

I'm exploring what infrastructure AI agents need to become useful autonomous workers without becoming uncontrollable.

Feedback welcome.

Popular repositories Loading

  1. gnom-hub-v1 gnom-hub-v1 Public

    Local multi-agent control hub — brainstorm freely, execute only when you press Execute. Python · FastAPI · no Docker.

    Python 1

  2. detektivspiel detektivspiel Public

    KI-basiertes Singleplayer-Detektivspiel – Pflichtenheft und Projektdokumentation

    Python

  3. tollgate tollgate Public

    Safety layer for AI agents — Protect · Route · Prove. Budgets, tool-loop hard stops, failover, chaos DR proof. OpenAI drop-in · MCP · n8n.

    Python

  4. awesome-ai-agents awesome-ai-agents Public

    Forked from aloth/awesome-ai-agents

    A curated list of AI agent frameworks, tools, platforms, research papers, and resources

  5. landjunge landjunge Public

    Profile

  6. awesome-mcp-servers awesome-mcp-servers Public

    Forked from punkpeye/awesome-mcp-servers

    A collection of MCP servers.