AI coding agent for your terminal. Reads, writes, edits code, runs commands. Any model. 14 kB.

CLAII = CLI AI Agent for coding. CLAII is a terminal-native AI pair-programmer with multi-agent orchestration, MCP toolchains, and context-aware, memory-persistent refactors across your codebase.

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

Caveman Distillate — ultra-compressed AI output mode. Distill text to its core. ~90 tokens, ~65% output savings. Claude Code skill.

⚡ A native app for all your coding agents.

Создание прокси на протоколе Vless с транспортом XHTTP через российские CDN

The GOAT AI harness, fed on gofio

A Go TUI framework with widgets, FSS styling, accessibility, reactive state, web backends, and agent tooling.

tuix is a simple and minimal terminal user interface framework

A component-based TUI framework for Go: two-pass layout, composable widgets, focus management, themes, and modal dialogs.

RETUI is a lightweight, component-driven framework for creating beautiful, interactive Terminal User Interfaces (TUIs) in Go.

llama.cpp fork with Maple-Preview support (ternary MoE): converter + full inference graph (hybrid SWA/GA attention, flash-head QK, 256-expert clamp-7 MoE)

An open-source database of AI models.

Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.

A minimalist, terminal-native coding agent written in C.

ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants

KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM

LLM inference in C/C++

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

CPU-optimized LLM inference engine (C)

Qwen3.6-35B-A3B local inference engine for Vulkan and Metal

An agent harness — a coding agent out of the box, open to anything you can wire a tool to. One hardened Go core, many front ends, pluggable in any language.

Small context, native speed, open all the way down — an open-source terminal agent runtime. One 12 MB Go binary, zero runtime deps.

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

The best minimalist coding agent harness and agent orchestrator.

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Northstar web browser, Open Source License: GPL v3. Northstar web browser is a real web browser, not based on Firefox or Chrome.

The most RAM efficient harness

The coding agent that answers to you, your model, your machine, your rules.

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors