freshcrate
Home > Databases > Jarvis

Jarvis

This bridge integrates Ollama into any chat interface and lets you build your own multi-agent pipeline, including a built-in memory database.

Description

This bridge integrates Ollama into any chat interface and lets you build your own multi-agent pipeline, including a built-in memory database.

README

Discord

TRION

TRION is a local-first autonomous AI system with a real runtime stack. It combines chat, tools, memory, container execution, and safety controls in one platform.

πŸš€ Quick Install & First Steps

Note: Make sure you have Docker installed and running on your machine before running the install script!

curl -fsSL https://raw.githubusercontent.com/danny094/Jarvis/main/install.sh | bash

Next Steps:

  1. Open your browser and go to http://localhost:8400 to access the TRION Web UI.
  2. Go to settings and add your preferred AI API Key securely to the Vault.
  3. Start a chat and ask TRION to write a simple script or test the home container!

✨ What You Get

  • Integrated Web Environment: Full Docker integration directly within the web interface.
  • Interactive Web Shell: Work seamlessly with TRION via a built-in web shell connected to its container.
  • Expandable Skills: Easily create, manage, and execute custom SKILLS.
  • MCP Integration: Native support for the Model Context Protocol (MCP).
  • Automation / Cronjobs: Schedule autonomous tasks and recurring operations.
  • Model Agnostic: TRION can be powered by local AIs (like Ollama) as well as external API-based AIs.
  • Advanced Memory System: Features a complex multi-layered memory architecture, including Graph-based STM (Short-Term), MTM, and LTM (Long-Term Memory).
  • Smart Context Storage: Automatically saves context based on your chat activity.
  • Daily Reflection ("Dreaming"): TRION "dreams" every day at 4 a.m. – meaning it autonomously summarizes and consolidates the daily conversation logs.

🏠 TRION HOME CONTAINER

TRION lives in its own dedicated, sandboxed containerβ€”its home. Inside this secure environment, TRION can test projects, run code, and try out new things automatically. You can completely customize this workspace and even trigger autonomous container tasks using cron jobs.

πŸ”’ Security First

  • Encrypted API Keys: Your API keys are entered once and securely stored using strict encryption.
  • Zero Raw Access: When working in the sandbox, TRION only has access to the names associated with the keysβ€”never the raw keys themselves. It cannot accidentally expose or leak your API credentials.

Would you like to help build TRION? Here you can find more information

πŸ“Έ Screenshots

🎨 Agents' Workspace


Displays the daily summary & reflections.
βš™οΈ Backend Control Layer


Visualizes the strict multi-tier intelligence flow.
🧩 Web UI Plugins


Extending functionality via web-based integrations.
πŸ”’ Security Vault


Fully encrypted API keys isolated from the sandbox.
πŸ“¦ Container Sandbox


Safe local execution environment for skills.
πŸ’¬ Main Interface


Seamless and beautiful chat interaction.

🀝 Support

If this project helps you, consider supporting development:

Sponsor danny094Kontakt: trlon.devs.dk@gmail.com

Release History

VersionChangesUrgencyDate
1.3.2## βœ… Phase 3.5: Chat Migration to Admin-API (55 min) - COMPLETE **Goal:** Move /api/chat endpoint from lobechat-adapter to admin-api **Implementation:** - Copied /api/chat logic from lobechat-adapter - Integrated LobeChat adapter for request transformation - Added CoreBridge integration for full pipeline - Implemented streaming support (NDJSON format) - Added error handling and logging **Files Modified:** βœ… adapters/admin-api/main.py β†’ Added /api/chat endpoint (239 lines) βœ… adaptLow1/8/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

TV-Show-Recommender-AIπŸ€– Recommend TV shows by matching favorites, averaging embeddings, and finding similar titles using fuzzy search and vector similarity.main@2026-04-21
agentic-ragπŸ“„ Enable smart document and data search with AI-powered chat, vector search, and SQL querying across multiple file formats.main@2026-04-21
vector-cache-optimizer⚑ Optimize vector searches with a hyper-efficient cache that uses machine learning for faster, smarter data access and reduced costs.base-setup@2026-04-21
AnyCam2RosπŸ“· Transform any camera into ROS2 image topics for seamless integration with robotic systems and effective VLA model deployment.master@2026-04-21
Flipkart-Product-Recommender-RAGπŸ›’ Build a leading-edge e-commerce recommendation system using RAG architecture, Groq Llama 3, LangChain, and AstraDB, deployed on Kubernetes for scalability.main@2026-04-21