LLMs & Model Tooling
Model-layer infrastructure: training, fine-tuning, prompting and everything that wraps a large language model.
A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
Dryforge : New generation of harness engineering - Claude Code & Codex Plugin.
Approvable, local-first AI coding agent for regulated teams: policy controls, governed MCP, evidence packs, audit trails, secure remediation, and any OpenAI-compatible model.
Agent Deck
Granite Switch — Build AI models like you build software
Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with free AI, cloud providers, or local Ollama models.
Handling 10M+ docs using RAG with zero hallucinatons
AgentGuard: Zero-Trust Security Foundation for AI Agents
CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?
Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.
A complete collection of RAG interview questions, answers (505 questions & 41 RAG types), system design scenarios, architecture patterns, and production-ready concepts.
An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.
Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
OpenDART 전자공시MCP | 83개 API → 15 MCP 도구. 공시·재무·지분·XBRL + 버핏급 애널리스트 프레임(내부자 시그널·회계 리스크·퀄리티 체크리스트) + HWP/PDF 첨부 마크다운화 | 83 Korean DART disclosure APIs → 15 MCP tools with Buffett-grade analyst frames
Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsurf, Hermes and any MCP client.
Visual knowledge bank for understanding large language models, with 180 concept cards from tokenization to deployment.
Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.
A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.
Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.
AI framework for Ruby/Rails developers
TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.
Annotate any page in Chrome and send the screenshot, selected element metadata, and your instruction directly into OpenCode.
Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models
ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full log stays on disk for when something actually fails. Cut the noise on the wire.
Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.
Launch multiple sandboxed profiles of any AI CLI or IDE - each with its own auth, config, and extensions.
Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.
Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.