Tools for Aider

AI pair-programmer harness with an Architect mode that splits planning (one LLM) from coding (another), and git-aware tooling that uses version control as the undo mechanism instead of custom state rollback. The best reference for multi-file editing tool design and planner/coder layer separation

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

by smtg-ai - A terminal app that manages multiple Claude Code, Codex, and other local agents (including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously

Ruler — apply the same rules to all coding agents

(1.4k ⭐) - An HTTP API for Claude Code, Goose, Aider, and Codex

Catalog of 80+ terminal-native AI coding agents (open-source and proprietary) plus the harnesses that orchestrate, sandbox, and extend them: session managers, parallel runners, autonomous loop infrastructure, and credential vaults. The most comprehensive reference for the CLI agent layer that most harness infrastructure is designed to host

Deterministic scheduler for 40+ CLI coding agents running in parallel git worktrees with an HMAC-signed audit chain, signed agent cards, and per-artefact lineage. The zero-LLM coordination loop and tamper-evident audit trail make it the only open-source orchestrator designed for compliance-sensitive agent fleets

Unified TUI and CLI to index and search local coding agent session history across 11+ providers including Codex

One TUI covering sessions across Claude Code, Codex, Gemini, and OpenCode, with live status and resume for each.

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

Dashboard spanning multiple machines, adding memory search, code-graph queries, and agent-to-agent messaging. Claude, Aider, Cursor.

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.

Chinese best practices for 8 AI coding tools (Claude Code, Cursor, Copilot, Windsurf, Gemini CLI, Kiro, Aider, Trae) with copy-paste config templates and multi-tool collaboration workflows

Self-hosted, local-first observability and kill switch for coding agents, reading Gemini CLI sessions alongside Claude Code, Codex, Cursor, OpenClaw, Aider, Goose, and others. Reads the session logs the runtimes already write on disk, so there is no SDK and nothing in the request path. Shows sessions, transcripts, tool calls, tokens, and cache-aware cost per session and model; an opt-in emergency

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.

REPL framework for Neovim. Supports Codex as a REPL target alongside Python, R, etc

Dynamic map of chat-related repository files with their function prototypes and related files, ranked by relevance, based on Aider's Repo Map

Collection of system prompts from production AI coding agents (Claude Code, Gemini CLI, Cline, Aider, Roo Code)

Local-first TUI and report generator for AI coding-agent session logs. Tracks cost, tokens, latency, tool failures, health, diffs, and CI gates across Claude Code, Codex CLI, Gemini CLI, Qwen Code, Cline, Cursor exports, Aider, OpenCode/OpenClaw, Kimi CLI, and generic JSON/JSONL traces

Engineering management layer for 34 specialist AI agents covering the full SDLC (architect, pm, senior-dev, code-reviewer, qa, security, devops, l3-support + 18 archetype-specific reviewers). 25 archetypes auto-detected with compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Multi-platform — Claude Code, Cursor, Codex CLI, Aider, Continue. Local kanban board, OWASP LLM Top 10 scanner, MI

Local workspace that runs coding-agent CLIs (Claude Code, Codex, OpenCode, Kimi, Qwen, Hermes, Aider, and others) side by side in tmux, driven from a TUI, a loopback-only Web UI, or the CLI, with an opt-in stdio MCP server that lets one agent spawn, read, steer, and stop the others. Apache-2.0

Local-first, Git-native CLI harness for repo-local coding-agent work, recording task state, accepted plans, verification evidence, and finish records inside the repository

AI-powered VMware vCenter/ESXi monitoring and operations: inventory queries, health/alarms, VM lifecycle (create, delete, snapshot, clone, migrate), vSAN management, Aria Operations analytics, and scheduled log scanning. Supports Claude Code, Gemini CLI, Codex, Aider, Trae, Kimi, and MCP

Persistent cross-session memory MCP server for 13+ AI coding tools. SQLite-backed state survives context resets and keeps Claude Code, Cursor, Gemini CLI, Codex, Windsurf, Amp, Kiro, VS Code Copilot, Trae, and more in sync. Install: npm install -g @egchq/egc

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, OpenClaw, Windsurf, Aider, Copilot, and AGENTS.md-compatible agents

Privacy-first local voice dictation menu bar app for macOS. Pairs with Claude Code, Cursor, Codex, and Aider to dictate long contextual prompts; transcribes via WhisperKit on Apple Silicon, pastes at the cursor, ~8 MB, MIT

Discover, create, edit, toggle, copy, move, and delete agent skills across 11 tools (Cursor, Claude, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment) from the terminal

Runs unattended against a shared bead queue (SQLite, atomic claims), dispatching each bead to a headless CLI — Claude Code, Codex, OpenCode, Aider — with every outcome routed through an explicit state machine; no inter-agent channel, coordination is done at decomposition time.

Desktop GUI over tmux where each session holds agent and shell tabs with per-tab working directories; waiting agents raise a header counter you can answer without switching tabs, and ntfy push carries it to your phone. Linux, macOS, Windows. Claude Code, Codex, Gemini, Aider.

Tool-agnostic AGENTS.md authoring kit (MIT) with 15 stack-specific templates, a tool compatibility matrix, an npm CLI + GitHub Action linter (agents-md-lint), and a migrator (agents-md-migrate) that converts .cursorrules, CLAUDE.md, Copilot, Windsurf, Cline, and Aider configs to AGENTS.md. Works across Cursor, Claude Code, Copilot, and 30+ AI coding tools. Free and open source

Rust TUI that supervises a fleet across many repositories at once, in durable tmux sessions you can approve from your phone.

Browse and monitor historical session records of AI programming tools (Claude Code, Codex CLI, Cursor, Aider)

Runs Gemini CLI, Claude Code, Codex, Aider and opencode inside a Linux micro-VM on a copy-on-write clone of your project, with a network allowlist and a pull-request-style diff review before changes are applied

Live tmux TUI with session groups, resume and fork, diff review, and mobile push when an agent needs an answer. Claude Code, Codex, Gemini, Aider, Amazon Q, OpenCode.

Trust-based delegation with quality ratcheting that commits improvements and reverts regressions. Chains Claude Code, Aider, Gemini CLI, Ollama.

Universal AI API proxy — hot-switch between 14+ LLM providers (GitHub Copilot, OpenAI, Anthropic, DeepSeek, Groq, Ollama, and more) from any AI coding agent without restarting sessions. Local proxy with automatic Anthropic OpenAI protocol translation, account rotation, and real-time usage tracking

Skill router and context picker for coding agents: a local model (via Ollama, offline by default) routes each prompt to the right skill via hybrid BM25 + embedding retrieval, cross-encoder rerank, and an LLM judge, then assembles a minimal context bundle for the execution model. Built-in prompt-injection gate scans every retrieved document, fail-closed. Ships an MCP stdio server and an OpenAI-comp

Full-cycle software development skill — plans, builds, tests, lints, fixes bugs, and writes production-grade docs. Auto-detects project state and adapts its 8-phase pipeline. Works on 9 AI coding agent platforms (Apache 2.0)

Turns a Gemini CLI chat from ~/.gemini/tmp/*/chats (the JSONL format with rewinds and patches, or the older JSON files) into a self-contained HTML replay with a scrubbable timeline, diffs and terminal output, with API keys and other secrets masked locally first. Share it as a link through a secret gist on your own GitHub, embed it, export a Markdown transcript for a pull request, or have its GitHu

Local-first project memory CLI for coding agents (Claude Code, Codex, Cursor, Aider). Indexes repo structure into greppable JSONL, retrieves task-scoped context via BM25 with optional local embeddings, and tracks staleness via source hashes. No LLM calls, no server. Apache-2.0

Policy layer for multi-agent workspaces: a JSON file sets what each path is worth, agents dry-run cleanup plans, and actions land in a hash-chained journal

Posts an itemized AI cost comment (tokens and dollars by model) on every pull request; tracks Claude Code, Cursor, Copilot, Aider, and any OpenAI/Anthropic API. Local ledger, never stores prompts. Open-source (MIT)

Checkpoint and rewind for any AI coding agent (Claude Code, Codex, aider) via isolated git shadow-refs that never touch your real HEAD, index, or branch, with best-effort conversation resume for Claude Code and Codex

Source for the sshepherd skill - credential-isolated SSH operations, service control, logs, configuration changes, Postgres introspection, and declarative deploys through preconfigured aliases (MIT)

Reviews plans, code, and commits with multiple coding CLIs

Failover for coding agents: when Claude Code hits a rate limit, ban, or outage, hands the task to Aider, OpenCode, or a local Ollama model, carrying context. Multi-provider and local resilience, not account evasion. Open-source (MIT)