[K] KernelCentral
Self-evolving Local-first

Kernel Central

A local-first AI agent that grows its own capabilities, discovers new skills, writes code, tests itself, and evolves, all on your own hardware.

v1.22.0 34 Skills Nemotron-3B 64k
K

3D Agent Avatar

How It Works

From user request to evolved capability in 7 steps.

01

User Request

A command or query triggers the pipeline.

02

Gap Detect

Analyzes if the request exceeds current capabilities.

03

Tier 1 Search

Search ecosystem and local repositories.

04

Tier 2 Synthesis

Code-generation of new skills when no match is found.

05

Critic Verify

Ephemeral replica reviews code for quality and safety.

06

User Confirm

Human confirmation gates the resolution.

07

Merge & Learn

Skill is merged into the ecosystem.

Anchored to real user failures • Human confirmation = reward signal • Trajectory fine-tuning on success
Architecture

The full system, across 22 ADRs.

The system is designed around a modular, tool-first philosophy. Every component is replaceable, every skill is independently testable, and the whole stack runs on consumer hardware.

Tool-First Pipeline

The model always has access to tools. Skills and routines are meta-tools in a native tool-calling loop. No routing-first triage.

ADR-022

Named Model Slots

Multi-slot architecture: primary (Nemotron), audio (Gemma 4), draft, embed — each independently managed with LRU eviction.

ADR-018

Multi-Provider Routing

GPU-accelerated model serving with Nemotron-3B (64k ctx) for local inference. Gemma 4 for audio. Ollama drop-in for cloud models.

ADR-013

Replica System

Ephemeral agent instances (critic, planner, pipeline roles) with isolated system prompts and named slot routing.

ADR-008

Think-at-Rest

Idle reflection: System 1/2 gap detection, identity and memory consolidation, proactive Telegram thoughts.

ADR-005

User-Request Evolution

Evolution anchored to real user failures. Only fires when a request genuinely fails. Human confirmation gates resolution.

ADR-020

Agent Auto-Discovery

Auto-discovers OpenClaw, coding agents (opencode, Aider, Claude Code), and peers via port scan, mDNS, and MCP.

ADR-015

Perceptive Context

Three-layer composable context: token-aware history, embedding retrieval, and skill-driven context providers built fresh per inference.

ADR-014
Live Status

System telemetry

Online
Status
6.2 VRAM / 16 GB
12d 4h Uptime
34 Skills
3 Peers
2h ago Last Evolve
0 Active Replicas
0 Queue
Get Started

Install and run locally.

terminal
# Clone the repository
$ git clone https://github.com/fabiopacifici-bot/kernel-evolving.git
$ cd kernel-evolving && bash install.sh

# Install the EVA CLI
$ ln -sf "$(pwd)/eva" ~/.local/bin/eva

# Start the agent
$ bash start.sh && eva /status

Kernel Evolving runs entirely on your own hardware. Everything is local-first with cloud escalation only for code synthesis. No data leaves your machine unless you explicitly allow it.

Requirements Python 3.11+, CUDA GPU (8GB+ VRAM)

Skills Catalog

34 skills

Every skill is autonomously generated, tested, and curated by the agent. Each one lives in its own git branch with a full SKILL.md spec, command interface, and test suite. Skills are synced from kernel-synthesized-skills .

Automation (4)

blog-intro-and-clarity-critique

/blog-intro-critique

Drafts a 3-paragraph blog introduction about why agent briefs matter, then critiques it for clarity.

rotate-old-logs-cron

/setup-log-rotation

Set up a cron job to compress log files older than 7 days and remove very old archives

self-evolution-assessment

/self-evolution-assessment

Analyze the last 24 hours of kernel evolution activity and write a concise self-assessment report

weekly-server-report

/weekly-server-report

Generate a weekly performance report from server logs and email it

Communication (5)

proactive-telegram-delivery-test

/test-proactive-telegram-delivery

Send a proactive Telegram message using a bot token and chat id from environment variables.

telegram-reminder-scheduler

/schedule-telegram-reminder

Schedule Telegram reminder messages by generating a one-shot send script and local scheduler instructions

translate-document-it-to-en

/translate-it-en

Translate a document from Italian to English while preserving basic formatting and document structure

translate_italian_to_english

/translate-italian

Translate the provided Italian text to English and save it to ~/kernel-evo-notes/translation.txt

website-change-monitor-telegram

/monitor-website

Monitor a website for content changes and send Telegram notifications when updates are detected.

Content & Media (3)

image-batch-resize-watermark

/resize-watermark-images

Resize a batch of product images and apply a text watermark for e-commerce use.

images-to-webp

/images-to-webp

Convert all images in a folder to optimized WebP format with configurable quality and recursion.

notion-markdown-sync

/sync-notion-notes

Sync local markdown notes to a Notion database via the Notion API

Data & Analytics (6)

extract-gdp-table-to-json

/extract-gdp-table

Fetch the Wikipedia GDP (nominal) page, extract the first 5 rows from the main country GDP table, and save them as JSON.

html-table-to-json

/html-table-to-json

Extract structured data from an HTML table and save it as JSON.

markdown-to-pdf

Convert Markdown files into PDF documents when a user needs shareable, printable, or archival output from Markdown content.

postgres-cli-csv-export

/build-postgres-cli-csv-export

Build a CLI tool that queries a PostgreSQL database and exports CSV

timeseries-anomaly-detector

/detect-timeseries-anomalies

Detect anomalies in a time-series CSV dataset and print alerts for outlier points

transcribe-meeting-and-extract-actions

/transcribe-meeting

Transcribe a meeting audio or video recording with ffmpeg Whisper and extract action items from the transcript.

Development (6)

github-pages-deploy

/deploy-github-pages

Deploy a static site from a local build folder to GitHub Pages

openapi-python-client

/generate-openapi-python-client

Parse an OpenAPI spec and generate a typed Python client package from it

python-code-review-fix

/review-python-fix

Review a Python function for bugs and improvements, then return a corrected version with inline comments explaining each change.

python-static-unit-test-generator

/generate-python-unit-tests

Generate Python unit tests for a module using static analysis of its source code.

python-unit-tests-roi

/generate-roi-tests

Generate pytest unit tests for a Python module containing calculate_roi(invested, returned) -> float

python-unit-tests-static-analysis

/generate-python-unit-tests

Generate unit test skeletons for a Python module using static analysis of source code.

Productivity (5)

article-summary-3-points

/summarise-article

Fetch an article from a URL and return 3 key points as a concise summary

summarize-article-key-points

/summarize-article

Fetch a web article and return its 3 key points as concise bullets.

summarize-web-article-key-points

/summarize-article

Fetch a web article and return 3 concise key points.

youtube-transcript-summarizer

/summarize-youtube-transcript

Fetch a YouTube video transcript and produce a concise summary

youtube-transcript-summary

/summarise-youtube-transcript

Summarise a YouTube video transcript into concise bullet points

Research (4)

ai-agent-paper-finder

/find-ai-agent-paper

Search online for AI Agents information and fetch the latest arXiv paper matching the topic.

arxiv-agentic-ai-scraper

/arxiv-agentic-ai

Search arXiv for papers about agentic AI and return a concise structured summary.

arxiv-recent-self-evolving-agents

/find-arxiv-self-evolving-agents

Find a recent arXiv paper about self-evolving AI agents and return the title and abstract

arxiv-self-evolving-agent-paper

/find-self-evolving-agent-paper

Find a recent arXiv paper about self-evolving AI agents and return the title and abstract

Utilities (1)

test-fallback

/test

Handles generic "test" tasks by echoing input and returning a successful result