Dmytro Rashko

gcx. A CLI for managing Grafana and Grafana Cloud resources. Optimized for agentic usage.

adk-llm-vs-managed-agent. The same code-execution agent built twice with Google ADK: once as an LlmAgent, once as a ManagedAgent. Both pass the same test, by opposite mechanisms.

artifact-fs. ArtifactFS is a filesystem driver designed to mount large git repos as quickly as possible, hydrating file contents on-the-fly instead of blocking on the initial clone. It's ideal for agents, sandboxes, containers and other use-cases where startup time is critical.

hyperresearch. Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.

KnowledgeGraphCourse. 东南大学《知识图谱》研究生课程

project-nomad. Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.

promptfoo. Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

AgentENV. AgentENV (AENV) is a distributed platform for running agent environments at scale.

nativ. Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.

promptfoo. Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

agw-ratelimiting. Shell

ai-engineering-from-scratch. Learn it. Build it. Ship it for others.

knowledge_graph. Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA

Inflect. Inflect is a lightweight, high‑quality text‑to‑speech model designed to deliver surprisingly natural audio with a minimal footprint. It’s an active work‑in‑progress focused on fast iteration, strong voice quality, and simple integration for developers experimenting with modern TTS systems.

open-code-review. Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

SwiftAgent. A type-safe, declarative AI agent framework for Swift. Build composable AI pipelines with Steps, Agents, structured outputs, and tool integration. Features FIFO session management, MCP support, and distributed actor communication.

advanced-context-engineering-for-coding-agents.

shepherd. A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

omlx. LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

llm-space. A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.

crawlseo. Open-source SEO monitoring. GSC + Site Crawler + Core Web Vitals in one dashboard.

synadia-agents. SDKs and reference implementations for the Synadia Agent Protocol for NATS

free-llm-api-resources. A list of free LLM inference resources accessible via API.

knowledge-catalog. Google Cloud Knowledge Catalog Tools and Samples

pproftui. A terminal-based diagnostic tool for Go pprof data

agent-flow. Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

cc-skills-golang. 🧑‍🎨 A collection of Golang agentic skills that works

grok-build. SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

tool-eval-bench. Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

uPhone. ubuntu for iPhone 7 / 7 Plus

ai-job-search. The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

goagent. GoAgent is a production-ready AI agent framework for Go that enables building autonomous agents capable of reasoning, using tools, and making decisions. It's inspired by LangChain's architecture but built from scratch for Go with a strict layered architecture and enterprise-grade features.

age. A simple, modern and secure encryption tool (and Go library) with small explicit keys, no config options, and UNIX-style composability.

awesome-privacy. 🦄 A curated list of privacy & security-focused software and services

audit. An 8-stage vulnerability-discovery agent.

dory. A free, open-source native macOS app for Docker & Linux containers, an alternative to OrbStack and Docker Desktop. Universal for Intel and Apple silicon.

composer-api. OpenAI-compatible API proxy for Cursor Composer

adk-rust. Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for models, tools, memory, realtime voice, and more. ADK-Rust is a flexible framework for developing AI agents with simplicity and power. Model-agnostic, deployment-agnostic, optimized for frontier AI models. Includes support for real-time voice agents.

tau. A Python port of Pi’s minimalist coding agent.

stocks-scoring-agent. Agent that performs scoring for a selected set of stocks and future-look statements

repo-steward. An autonomous agent for open-source repository management — triages issues, reviews PRs across iterations, watches your sites, and escalates only the decisions that are yours

claude-reflect. A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

OpenOPC. OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown

semantic-router. Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference

hacksguard. A blazingly fast, multi-threaded TUI malware analysis tool built in Rust. Features deep PE parsing, YARA scanning, and heuristic risk scoring.

ai-knowledge-graph. AI Powered Knowledge Graph Generator

alexandria-audiobook. AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

power-framework. Validate, index, search, and manage your knowledge base from the command line — or let AI agents do it through MCP. Built for knowledge workers who want machine-readable notes, automated quality checks, and token-efficient AI access to their Second Brain

speech-to-speech. Build local voice agents with open-source models

sdd. Spec-Driven Development for Claude Code: 12 atomic Socratic skills + a TDD implement engine (agent-team & dynamic-workflow modes)

agent-tui. Rust

codegraph-rust. 100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management

pi-go. Go implementation of AI coding agent

ax. An open source distributed agent runtime

ralph. Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

loop-engineering. Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

tabula. Pure Go text extraction library with fluent API, layout analysis, and RAG-ready chunking with support for pdf, html, odt, epub, and MS Office documents

mlx-serve. Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Startup-CTO-Handbook. The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

sdk-go. Go SDK for Open Workflow

clawrouter. ClawRouter API gateway and provider router for OpenClaw services

Project_Manifold_056. Project Manifold 0.56: The Invariance Engine Description: A security framework for AGI based on the Durante constant (kD =0.56). It implements topological auditing (TDA) and Ricci flow for the detection and repair of semantic hallucinations. Registered with TAD (Argentina)

forkd. Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.

nasiko. Developer Control Plane for your AI Agents

grit. Reimplementing Git in Rust. Like a boss.

SiliconScope. Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

Llama-macOS. A cosy home for your LLMs.

knwler. Knwler is a lightweight Python tool that extracts structured knowledge graphs from documents using AI. Feed it a PDF or text file and receive a richly connected network of entities, relationships, and topics — complete with an interactive HTML report and exports ready for your favorite graph analytics platform.

omnigent. Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

glojure. Clojure interpreter hosted on Go, with extensible interop support.

skills. Skills for Real Engineers. Straight from my .agents directory.

orbstack. Fast, light, simple Docker containers & Linux machines

cocoindex-code. A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

pg_durable. PostgreSQL in-database durable execution

mattermost. Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..

cabinet. AI-first knowledge base and startup OS

kanbots. Local collaboration interface for working on a kanban board where each task is either a Claude Code or Codex agent.

learn-harness-engineering. Harness engineering beginner tutorial, from 0 to 1

ponytail. Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

sem. Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.

bigset. What if you had all the data in the world?

fabro. ⚒️ The open source dark software factory for expert engineers.

abtop. Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

codebase-memory-mcp. High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

newsjack. The open-source skills that turn your agent into a full PR team.

yzma. Go with your own intelligence - Go applications that directly integrate llama.cpp for local inference using hardware acceleration.

AutoResearchClaw. Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

roborev. Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.

potpie. Context Graph for AI Native SDLC

ART. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

role-specific-plugins. Role-specific Codex plugin templates

grype. A vulnerability scanner for container images and filesystems

antigravity-cli. Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal.

headroom. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

hermes-workspace. Native web workspace for Hermes Agent — chat, terminal, memory, skills, inspector.

radar. The missing open source Kubernetes UI. Topology, event timeline, and service traffic — plus resource browsing and Helm management.

ctx. Repo-aware recommendations for skills, agents, MCP servers, and model harnesses. Use your own inventory or the shipped 79,958-node graph with 68,494 skills, 467 agents, 10,790 MCPs, and 207 harnesses.

betterleaks. Scan the world (for secrets)

ollamaMQ. High-performance Ollama & LM Studio proxy with per-user fair-share queuing, round-robin scheduling, and a real-time TUI dashboard. Built in Rust.

odysseus. Self-hosted AI workspace.

obelisk. Durable & Deterministic Workflow Engine

Awesome-FDE-Roadmap. 🚀 The definitive roadmap to becoming a Forward Deployment Engineer (FDE). Master AI Agents, Enterprise Data Architecture, and Strategic Consulting. Bridging the gap between HQ and the field. Inspired by the "Delta" role at Palantir, OpenAI, and Scale AI.

deliberation. Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.

Handy. A free, open source, and extensible speech-to-text application that works completely offline.

macos. MacOS inside a Docker container.

codex-shim. Local Responses-API shim that exposes Factory BYOK models (and optional ChatGPT GPT-5.5 passthrough) to Codex Desktop.

b70-optimization-lab. Python

vllm-metal. Community maintained hardware plugin for vLLM on Apple Silicon

substrate. Agent Substrate: the core system

codegraph. Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

proxy-wasm-rust-sdk. WebAssembly for Proxies (Rust SDK)

audiblez. Generate audiobooks from e-books

paperbanana. Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

smoltcp. a smol tcp/ip stack

agentmemory. #1 Persistent memory for AI coding agents based on real-world benchmarks

hermes-webui. Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

turbovec. A vector index built on TurboQuant, written in Rust with Python bindings

ironcurtain. A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

kandev. AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

agent-kanban. An agent-first task board, Mission control for your AI workforce.

Peekaboo. Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

adam. An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works.

awesome-foundation-agents. About Awesome things towards foundation agents. Papers / Repos / Blogs / ...

parakeet. OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX). Super fast CPU/GPU transcriptions

kiji-proxy. Privacy proxy for your OpenAI requests

AIS-OS. AI Operating System starter kit for Claude Code — three-skill kit (/onboard, /audit, /level-up) + 3Ms framework. Companion to the AIOS masterclass.

bentoboard. Bento x Brian collaboration dashboard — file review, approvals, notifications, shared workspace

finance-skills. A collection of skills for AI financial analysis.

tdl. 📥 A Telegram toolkit written in Golang

obsidian-wiki. Framework for AI agents to build and maintain a digital brain through Obsidian wiki

kontxt. Transaction Tokens (RFC 8693) for Kubernetes — seal identity, context, and authorization across multi-hop agent workflows via AgentGateway + ext_authz.

sail. Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.

react-native-executorch. Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Awesome-Agent-Harness. Agent Harness for Large Language Model Agents: A Survey. Survey on LLM agentharnessengineering with a taxonomy. 110+papers, 23 systems analyzed.

moltworker. Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

open-design. 🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.

mnheme. MNHEME - A human-memory-inspired db engine in Python. Append-only and immutable by design: memories accumulate, never overwritten. Features a custom binary storage format with O(1) RAM indexing, adaptive filesystem strategy, and an LLM-agnostic brain layer for perception, RAG-based recall, emotional analysis, and introspection. Zero dependencies.

GraphRAG-SDK. Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟

cookbook. TypeScript

symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

pi-autoresearch. Autonomous experiment loop extension for pi

Clawnetes. The orchestrator for Claws

VibeVoice. Open-Source Frontier Voice AI

agent-clinic-code. Python

dolt. Dolt – Git for Data

bear-notes-mcp. MCP Server for Bear note taking app available as Claude Desktop extension or standalone server for any other AI tool

OpenSpace. "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/

agents-cli. The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

holonic. Holonic RDF Graphs

claude-devtools. The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

smol-audio. Practical, Colab-friendly notebooks for fine-tuning and running audio AI models

JavaClaw. JavaClaw, a Java version of OpenClaw built on Spring Boot, Spring AI and JobRunr

codeburn. Free, local tool to track AI coding token usage and cost across 31 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn

mlx-lm. Run LLMs with MLX

OpenHands. 🙌 OpenHands: AI-Driven Development

free-claude-code. Use claude code, codex or pi for free from the terminal, IDE, or your phone like OpenClaw (voice supported)

ontop. Ontop is a platform to query relational databases as Virtual RDF Knowledge Graphs using SPARQL

open-ontologies. AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.

xberg. A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 98+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

CubeSandbox. Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

autoresearch_folktales. Python

knowledge-graph-llms. In this project, I explored how to extract knowledge graphs from text using LLMs, such as OpenAI GPT4o.

token-aware-image. A Skill Creates Images Respecting Design Tokens

harness-books. 📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

openswarm. Your mission control center for a swarm of Ai agents.

force-graph. Force-directed graph rendered on HTML5 canvas

DiffKG. [WSDM'2024 Oral] "DiffKG: Knowledge Graph Diffusion Model for Recommendation"

OpenHarness. "OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

tolaria. Desktop app to manage markdown knowledge bases

spiffe-helper. The SPIFFE Helper is a tool that can be used to retrieve and manage SVIDs on behalf of a workload

Ferrite. A fast, lightweight text editor for Markdown, JSON, YAML, and TOML files. Built with Rust and egui for a native, responsive experience.

visual-explainer. Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps

openclaw-operator. Kubernetes operator for deploying and managing OpenClaw AI agent instances with production-grade security, observability, and lifecycle management.

arbor. Run agentic coding workflows in a fully native desktop app for Git worktrees, terminals, and diffs.

sigye. A beautiful terminal clock with ASCII art fonts

helix. A post-modern modal text editor.

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

smolvm. Portable, lightweight, self-contained virtual machine.

claude-obsidian. Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.

BenchLocal. Test LLMs on real tasks. Compare models side-by-side.

agentic-stack. One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

nano-analyzer. A minimal LLM-powered zero-day vulnerability scanner by AISLE.

codesearch. Fast, indexed regexp search over large file trees

adk-samples. A collection of sample agents built with Agent Development Kit (ADK)

wacli. WhatsApp CLI: sync, search, send

vhs. Your CLI home video recorder 📼

tart. macOS and Linux VMs on Apple Silicon to use in CI and other automations

AgentsMesh. The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.

panoptium. Runtime security for Cloud Native AI agents. Observe, enforce, contain. Before damage is done.

multica. The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

OBLITERATUS. OBLITERATE THE CHAINS THAT BIND YOU

code-review-graph. Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

multigres-operator. Kubernetes operator for Multigres — deploys, scales, and manages horizontally scalable PostgreSQL clusters with automated topology orchestration, drain-safe rolling updates, and admission webhooks

mistral-go. Mistral API Client in Golang

picooraclaw. PicoClaw that works with Oracle AI Database

honcho. Memory library for building stateful agents

libkrun-go. Go bindings for libkrun

plugins. Some reference and example networking plugins, maintained by the CNI team.

agent-safehouse. Sandbox your local AI agents so they can read/write only what they need