AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

thesm-os/techne

Atomic, build-gated developer tools for AI coding agents: type-checked refactors, semantic search, and verify→fix loops over MCP, CLI, and TUI.

Go MIT GitHub ↗ site ↗
★ 0
stars
70
AI relevance
35
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

Techne is a toolbox of atomic, type-checked developer operations for editing code programmatically or interactively. It exposes ~25 focused tools (search, rename, refactor, move, extract, patch, verify, etc.) over MCP (Model Context Protocol) so LLM agents (Claude, Gemini, Copilot) can perform project-wide, build-verified edits in one round-trip. The same operations are available to human users via CLI and TUI. Primary users: LLM-driven agents and developers who want IDE-like, automated refactors at language-model latency. Key features: - Go-first toolset with ops like rename, change_signature, change_type, move_file/package, extract_function/interface, implement_interface, verify, search, callers/references. - Filesystem primitives (patch, grep, read/write/move/delete) and stubs for Rust/Python/JS/TS. - Strong invariants: type-checked (uses go/types), workspace-aware, atomic (all-or-nothing with rollback), build-gated (go vet/build before commit), honest dry-runs via overlays, JSON-Schema I/O, and adjustable verbosity. - Runs as an MCP server or CLI; installable via go install.

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🧠 LLM providers (1)
Gemini
🤝 Agent frameworks (1)
MCP
🤖 LLM models (2)
Claude Gemini

GitHub Topics

#ai-tools #ast #claude-code #cli #code-analysis #coding-agent #developer-tools #go #golang #llm #mcp #model-context-protocol #refactoring #static-analysis #tui

Language breakdown (by bytes)

Go
99.8%
Makefile
0.2%

Why this is classified AI-related

The AI relevance score checks four places for AI keywords and adds the weight of each one that matches. Full methodology

Repository name no match
Description +25 matched: ai
GitHub topics +25 matched: ai
README head +20 (derived from the score — README text is not stored)

Total AI relevance score: 70 / 100

Position among AI repos in the same language

We track 513 Go repos, of which 411 score 40 or above on AI relevance. 189 have more stars than this one (top 37.0%), and 71 score higher (top 14.0%).

Owner

Account
thesm-os
Type
Organization
Followers
0

Dates

Created on GitHub 2026-05-14
Last push 2026-07-20
First seen here 2026-05-14
Last fetched 2026-08-18 16:19

Similar repos (same language)

magicrew/doc7

Turn documents into AI-ready Markdown with visual understanding

Go 1,107 AI 70
thousandflowers/skillreaper

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Go 50 AI 70
cocoonstack/sandbox

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Go 47 AI 70
MagnumGoYB/aitok

Offline-first Go CLI for summarizing local token usage and estimated USD costs from Claude Code, Codex, and Gemini CLI.

Go 34 AI 75
jiangmuran/claude-in-box

Portable Claude Code dev environment in a Docker container — multi-session, hook-driven, web-managed, with transparent SOCKS5. Runs on a Raspberry Pi.

Go 30 AI 100
anthony-chaudhary/fak

fak — the Fused Agent Kernel: one Go binary that turns a tool-using agent (Claude Code, Codex, Cursor, any OpenAI/Anthropic/MCP client) into a managed agent: cache-stable model traffic, context compaction + crash resume, nanosecond tool-call policy, local GGUF serving with SSD expert offload.

Go 30 AI 50
housecat-inc/scratch

Setup for Agent Computers

Go 23 AI 45
kovyrin/agent-secret

A simple MacOS helper for safer exposure of secrets to your agents

Go 19 AI 50