skills.rest
OriNachumOriNachumCommunity·7 Agent Skills Included

autonomous-intelligence

Local companion robots, on-device inference, memory, and speech

Builds always-on local AI companions that see, hear, speak, and remember across a single continuous conversation. Runs Gemma and Qwen models on NVIDIA Jetson and Raspberry Pi with Docker, vLLM, Triton, and OpenAI-compatible APIs. Adds layered memory with MongoDB vector search and Neo4j knowledge graphs, plus skills for planning, deploying, testing, and speaking. Removes cloud dependency, manual model setup, and fragmented device configuration.
234|15
↗
npx skills add OriNachum/autonomous-intelligence --all -g -y
Available:

Gives coding agents the repository's build, lint, test, and session commands plus style and safety rules so they can work on the codebase consistently.

All Skills in This Repository (7)

Pure Emerald Level Indicators
📦 In Repo
OriNachumOriNachum

memory

Manage AI agent memory with notes, MongoDB RAG, and Neo4j graphs.

Community
Advanced
📦 In Repo
OriNachumOriNachum

mongodb-query

Query MongoDB notes for memory analysis and statistics.

Community
Intermediate
📦 In Repo
OriNachumOriNachum

plan

Generate detailed architectural or execution plans and save them as timestamped markdown files.

Community
Basic
📦 In Repo
OriNachumOriNachum

call-qq

Send messages to the 'qq' agent from a command-line interface.

Community
Basic
📦 In Repo
OriNachumOriNachum

neo4j-query

Query Neo4j knowledge graphs to retrieve entities and relationships.

Community
Intermediate
📦 In Repo
OriNachumOriNachum

implement

Execute code changes and shell commands from plan files in docs/plan.

Community
Intermediate
📦 In Repo
OriNachumOriNachum

coding

Assist with writing, debugging, and reviewing code across multiple programming languages.

Community
Intermediate

Frequently Asked Questions

FAQPage Schema
How to install autonomous-intelligence?▼

Run `npx skills add OriNachum/autonomous-intelligence --all -g -y` in your terminal to install all skills in this suite globally.

How to run local AI models on NVIDIA Jetson?▼

The gemma subprojects provide ready Docker Compose setups for vLLM, Triton, Transformers, and SGLang serving Gemma 3n with OpenAI-compatible endpoints on Jetson devices.

How to give an AI assistant long-term memory?▼

The memory skill combines protected core notes, MongoDB vector search, and a Neo4j knowledge graph so facts, entities, and relationships persist across conversations.

Can I build a voice companion robot with this project?▼

Yes. The Tau and reachy-mini components wire together wake-word listening, speech-to-text, text-to-speech, camera vision, and face detection into one continuous conversation loop.

Does it work without cloud API keys?▼

Yes. The newer components run fully local models on Jetson or DGX Spark, though the original Tau setup optionally uses OpenAI, Voyage, and Pinecone keys.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills