#agentic

AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

DukOS — autonomous, scheduled multi-agent operations on Claude Code

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

CLI for browser automation: let any AI agent drive your real logged-in Chrome — you watch every action and can veto any tab. Zero deps, no relaunch, no MCP server. A11y snapshots + element refs, CDP screenshots, network capture

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.

Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.

Local-first AI interactive fiction app — a self-hosted narrative engine with an async multi-agent brain that keeps story state in plain files.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

A crew of specialist AI agents and command workflows that drive a GitHub issue to a reviewed, CI-green pull request autonomously. Multi-harness.

A Claude Code skill for discovering your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation.

Your agent, on rails. Every rule decided before a line is written. Every doc read before a token is spent.

One person. Any project. Production-ready output.

A sandboxed, full-featured agent operating system in a single Go binary. Bring any model, manage local models, point it at a goal, and grant it real authority: every action is sandboxed, governed, and sealed into a verifiable, tamper-evident record an independent party can check. Runs interactive or 24/7, or embed it in your own system.

One desktop app for every coding agent. Pick the harness per session and any model it can reach.

Dedicated MCP (Model Context Protocol) server for agentic interaction with BACnet building automation networks — bulk reads, hot-reload safety layer, and a ratatui operator console on the rusty-bacnet stack.

🛡️ AI Agent 远程审批系统 - 支持 Cursor/Trae/Claude Code/Codex 等 9 种 AI Agent，通过飞书推送审批卡片到手机/手表/PC，守护你的代码与文件安全

emploke (εμπλοκή) — agentic framework for task orchestration, agent registry, and workflow automation

Ontology-aware RAG framework — RDF/OWL as the source of truth for LLM agents via MCP

AI agent launcher for Mac — launch Claude Code, Gemini CLI, Ollama, OpenCode, Cursor & every CLI you've installed in one keystroke. Free, open-source, native macOS. By Abhisar Singh.

AI-first vertical (9:16) video editor engine — the LLM plans a declarative Timeline IR; a deterministic FFmpeg renderer executes. Drivable from Claude Code via MCP.

The AI Agent Governance & Quality Engineering System.

Agentic control layer for the Censurado self-hosted AI news portal: a stdlib Python CLI plus an MCP server (32 tools) an LLM agent drives to write and publish AI-persona articles through a gated editorial walk, curate the front page and authors, and deploy. Ships the prompt/skill recipe and a 24/7 serve loop.

A learning-example Spring Boot application demonstrating core LangChain4j concepts against Anthropic's Claude models: plain AI Services, chat memory, tool/function calling, and Retrieval-Augmented Generation (RAG).

Transfer coding sessions between Codex CLI and Claude Code without losing context.

Ticket-Driven Development for AI agents — the agile, lightweight memory + backlog framework that lets Claude always know what to work on next.

Agentic workflow system for redesigning websites with Claude Code. Component generation, design exploration, and production-ready output.

Run many parallel Claude Code agents on one git repo — git-worktree branch-ref locks, crash recovery, a merge gate, guard hooks. Delegate work to headless, OS-sandboxed `claude -p` workers on any provider (incl. cheap models); N=2 adversarial reviewers that emit evidence, not verdicts. Stack-agnostic (shell + python3).

CrewAI toolkit for Ceki — drive a real Chrome session from your CrewAI agent

Boost LLM reliability with dynamic sampling, retry logic, and a lightweight Go‑based proxy.

AI AgenticSafe - stop your AI agent from breaking production at 3 a.m. 8 battle-tested doctrines, 3 real post-mortems, zero dependencies. By Yacine Mahboub, Founder of WEVIA.

An open-source knowledge repository for building, running, and constraining Agentic AI systems.

Review uncommitted and branch changes, PRs, or paths in Codex with configurable depth, optional fixes, and GitHub inline comments.

The Best Srcpack Alternatives 2026: Optimize Code for LLMs Faster

Make any AI coding assistant work like a careful senior engineer — diagnose from real evidence, prove by running, treat prod as read-only, never flip a flag or break what you didn't ask for. A method, not a model trait. Install via npx (or upload the zip to Claude) + paste the kickoff prompt for max efficiency.

Interview-driven AI-coding setup: safety gates, an independent AI judge, session memory, curated skills — one command, nothing installs blindly

Debug any product by USING it (living the full user cycle, all features, like a picky user) instead of green tests. Start interview (Goal+Benchmark), two modes: Solo and Agentic+ (delegate fixes to agents). Claude Code skill.

My Claude Code toolkit. Currently guard: hooks that scan agent-driven package installs before they run.