#developer-tools

The lifecycle automation layer PostHog doesn't have yet. Code-first email journeys on PostHog + Resend. Self-hosted.

MCP server for 1С:Enterprise — AI assistant sees your configuration and generates accurate BSL code. One binary, zero dependencies, 10 tools.

MGR — Método Governado por Rastreabilidade (Traceability-Governed Method): spec-driven development framework for coding agents, portable between Claude Code and GitHub Copilot

Spec-first development toolkit for agentic AI coding agents — skills + guardrails for Claude Code, Codex, Cursor, Antigravity, and more.

🦈 Shark AI - AI-Native Collaborative Development Tool powered by StackSpot AI and BMAD Method

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

Yet another coding agent harness, lightweight and written in go.

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.

Skill distribution

Semantic code search for coding agents — search by meaning like grep, trace call graphs, find tests & blast radius. 100% local embeddings (ONNX/MLX), MCP server, plugins for Claude Code, OpenCode, Codex & Droid.

Persistent memory for pi — learns corrections, preferences, and patterns from sessions

Smart auto-mode for Claude Code. The safe alternative to --dangerously-skip-permissions.

The local-first control layer for your AI coding CLIs — one context, one cross-repo fleet view.

该仓库未发布描述。

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

Local-first control plane for AI coding agents: repo memory, verification, sessions, and dynamic workflows.

🧠 Self-hosted, privacy-first MCP server for long-term AI memory — save, search & summarize Claude/ChatGPT chat history locally. No cloud, no database.

Tera templating + smart [vars] for self-rendering TOML configs (planning stage)

A reliable file downloader with durable resume, parallel segmented downloading, and optional integrity verification.

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

GCC diagnostic UX wrapper for GCC 9-15 that keeps terminal output shorter, root-cause-first, and fail-open.

Multi-repo manager (TUI & CLI) for git and jj with parallel dispatch and live status

CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

Organized AI Workspace | Complex Multi Phase Planning | Auditable Agent Workflows | Long Running Goals | Structured Agentic Loops

Generate smart commit messages from git diff with CommitMe, a lightweight Pi extension.

Code-owned AI review for pull requests

SpecScore CLI — lint, query, and scaffold SpecScore specifications.

Intent-driven idea development system for AI-assisted work.

Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.

Memory for AI coding agents — remembers what goes wrong, reminds you before it happens again. One Go binary, no embeddings.