All Coding Agent tools (131)
- CC Safety NetA PreToolUse hook that blocks destructive Git and file commands and secret access before AI coding agents run them, defeating reordered flags, shell wrappers, and one-liners.
- cmuxOpen-source Ghostty-based macOS terminal built for coding agents: vertical tabs, notification rings when agents need attention, split panes, an in-app browser, and a CLI/socket API.
- DeepSeek HarnessMIT agent runtime. Pay model API only. Live Flash peak $0.44/$1.32 per 1M, not the old $0.14/$0.28 row.
- EmdashYC W26 ADE. Desktop $0; Cloud is contact.
- Grok BuildxAI's Rust CLI coding agent. The live GitHub repo is superagentic-ai/grok-cli. Auth is Grok.com or an xAI API key.
- HerdrOpen-source runtime that keeps your coding agents alive: real terminal sessions on a background server, so Claude Code, Codex, and opencode keep working when.
- LuvusLuvus is Apache-2.0 Rust mission control that watches, resumes, and orchestrates coding agents in one TUI.
- MulticaOpen-source workspace that assigns issues to coding agents as teammates. Self-hostable, 26 CLIs, daemon runs on your machine.
- NVIDIA NOOANVIDIA's open-source agent framework that turns an agent into one Python class: methods are actions, docstrings are prompts, at 82.2% SWE-bench Verified.
- Open AgentsVercel Labs' MIT-licensed reference app for running background coding agents: a web UI, a durable workflow runtime, and isolated sandboxes you can fork.
- ReasonixDeepSeek-native AI coding agent for the terminal. A config- and plugin-driven harness in a single static Go binary, tuned around DeepSeek's prefix cache to k.
- ShipAnyAgent-native AI SaaS template family: auth, payments, subscriptions, credit billing, i18n, storage, and AI generation pre-wired so coding agents can ship AI.
- SoL-PiSoL-Pi is NVIDIA's MIT Pi extension that cuts agent tokens with four opt-in mechanisms and no patch to Pi itself.
- SupersetSource-available desktop app (Elastic License 2.0) to run an army of CLI coding agents in parallel — Claude Code, Codex, OpenCode, and more — each in its own.
- Vibe SquadMulti-model coding harness: one coordinator routes 71 Markdown specialists across Codex, Claude, Gemini, Grok, and Kimi in git worktrees.
- InsForgeOpen-source agent-native backend: Postgres, auth, storage, edge functions, compute, hosting, and a model gateway driven by CLI and MCP.
- AI Data ExtractorAI Data Extractor is an MIT Python toolkit that pulls local chat history from Claude Code, Cursor, Codex, and other coding agents into JSONL.
- AI Job SearchAn open-source Claude Code framework that runs your job search locally: scrape postings, score fit, tailor your CV, draft cover letters, and prep for interviews.
- AiderOpen-source terminal pair programmer. Apache-2.0 and BYOK. You pay the model API, not an Aider seat.
- aiXcoderChinese AI coding assistant with an Apache-2.0 7B model. No public SaaS price table; treat cloud seats as sales-quoted.
- Amazon Q DeveloperAWS coding assistant for IDE, CLI, and console. Free tier plus a $19/month Pro plan after the June 2026 rename.
- AmpSourcegraph agent. Not a Cody rename; not $10/day unconstrained Opus.
- AnteAntigma Rust harness. Public repo Apache-2.0; binary free in preview. CLI $0 plus BYOK or local GGUF. Not a $20 seat.
- Augment CodeEnterprise coding agents. Enterprise custom. Not Indie $20.
- Autohand CodeSelf-evolving terminal agent. CLI $0 plus BYOK. Enterprise is sales, not a public $20 seat.
- Bolt.newStackBlitz in-browser app builder. Not an unlimited no-install slogan.
- Chrome DevTools MCPGoogle's Apache 2.0 MCP server that lets coding agents drive a live Chrome browser for debugging, automation, and performance traces.
- Claude CodeAnthropic's agentic coding tool for terminal, IDE, desktop, and browser. Reads the repo, edits files, runs commands, and connects MCP, skills, and hooks.
- CLI-AnythingHKUDS open-source registry that turns GUI apps, APIs, and SaaS tools into agent-native CLIs for OpenClaw, Claude Code, Codex, and Cursor.
- ClineOpen-source VS Code/CLI/SDK coding agent. Enterprise custom. Not a Claude 3.5 Sonnet wrapper.
- code-testing-generatorMicrosoft's open-source polyglot agent that researches a repo, then plans, writes, and verifies unit tests: 92.1% completion versus 78.9% for stock Copilot.
- CodebuffYC terminal agent. Public seats $100 / $200 / $500 plus 1¢/credit. Not a $20 Cursor twin.
- Codex CLIOpenAI's terminal coding agent: inspect the local repo, edit files, run tools, review diffs, and automate with codex exec. Billed through ChatGPT plans.
- CodySourcegraph's enterprise AI coding assistant. Chat, auto-edit, and prompts over local plus remote codebases via Sourcegraph Search.
- Command CodeAI coding agent from Command Code AI that learns your coding taste with taste-1, then ships, reviews, and refactors in your style from the terminal.
- ConfirmoYour AI coding companion that lives on your desktop - a charming desktop pet powered by Claude AI
- Context ModeAn MCP server and plugin that stops context-window bloat in AI coding agents, sandboxing MCP tool output into a searchable SQLite index and recovering it on demand.
- ContinueOpen-source coding agent for VS Code and JetBrains. Apache-2.0, local models, CLI, and MCP. Acquired by Cursor; the repo stays public.
- CrushCharm terminal agent. CLI $0. Hyper Free $0 / Sub $20. Not a Claude seat.
- Origin (by Cursor)Cursor's Git forge and code-hosting platform built for AI coding agents, with repos, pull requests, GitHub sync, and agents in every repo.
- CursorAnysphere's AI IDE: Individual $20, Pro $40, Teams $40/user. Cloud agents and Bugbot are billed on top of the seat.
- DevinCognition's cloud software agent. Core is $500/month. A $20 Devin A//2 seat exists. Desktop product is Windsurf.
- Eigenwise ToolshedEigenwise Toolshed is six MIT Claude Code plugins for repo maps, live rules, tickets, extra models, and local usage.
- Everything Claude CodeComplete Claude Code configuration collection from an Anthropic hackathon winner. Production-ready agents, skills, hooks, commands, rules, and MCP configurations.
- Factory DroidFactory coding agents. Not a 58.75% Terminal-Bench census.
- GitHub CopilotGitHub's AI coding assistant for IDE, CLI, mobile, and cloud agents. Completions, chat, PR drafts, and paid plans from Free to Enterprise.
- GLM Coding PlanZhipu's coding subscription. Recurring seats: Lite $10, Pro $30, Max $60. Includes GLM-5, not unlimited $3 GLM-4.7.
- Google AntigravityGoogle's agent-first IDE at antigravity.google. Public preview remains free. Do not treat a Windsurf acquisition as a first-party fact.
- ChatGPT ProOpenAI top ChatGPT seat. Not unlimited o1-mini / GPT-4o; not the API.
- HalvDesktop workspace for Claude Code, Codex, Kimi, and GLM. Keep your subscriptions. macOS, Windows, and Linux. 7-day trial.
- HapiLocal Happy alternative. Wraps official CLIs; no public dollar seat.
- herdrmNative macOS console for herdr: see every coding agent across machines and jump into its live terminal.
- Junie (JetBrains)JetBrains' LLM-agnostic AI coding agent that ships code from your terminal, IDE, or CI/CD pipeline, with bring-your-own-key model support.
- Kilo CodeOpen-source VS Code/CLI agent. BYOK or Kilo Gateway. Not a 1.4M-install census.
- Kimi Code CLIMoonshot terminal agent. K2.7 Code API is CNY, not unlimited $19 K2.
- KiroAWS AI IDE and the new name for Amazon Q Developer. Free plus Pro at $20/month. CLI install is `curl https://cli.kiro.dev/install | bash`.
- magiOpen-source terminal coding agent that makes agents justify 'done': a council of three auditors votes on whether the evidence backs the finish.
- ManusManus is an action engine for slides, sites, design, research, and browser tasks. Official banner: it will soon operate as an independent company again.
- MarblismAI employees, not a 60s Next.js generator. 50h included.
- MiMo CodeXiaomi terminal agent. OpenCode fork. CLI $0; Xiaomi OAuth or BYOK. Not a published dollar seat.
- MiniMax CodeMiniMax Code is an MIT terminal coding agent you run as mcode, with MiniMax login or your own OpenAI-compatible API.
- Mistral VibeMistral terminal agent. CLI $0 plus Mistral API key. --agent auto-approve / --yolo. Not a $20 seat.
- Muse CodeMeta's terminal coding agent powered by Muse Spark 1.2. Install with one command, run persistent background agents across large repos, and pay per token instead of per seat.
- NVIDIA Nsight AINVIDIA CUDA MCP server and Nsight Copilot for coding agents. Hosted docs MCP plus an Apache 2.0 self-hosted blueprint.
- ompomp (Oh My Pi) is a batteries-included terminal AI coding agent built on Pi: hash-anchored edits, native LSP refactors, DAP debugging, browser automation, and first-class subagents.
- OpenChamberOpenChamber is an MIT agentic workspace on OpenCode for desktop, web, VS Code, and phone, with Private Relay and multi-run.
- OpenClaudeOpen terminal agent. MIT for contributor changes; derived from Claude Code. CLI $0 plus BYOK.
- OpenCodeMIT open-source coding agent for terminal, IDE, and desktop. 198k GitHub stars. Bring any model, or use free included models and Zen.
- Orca ADEOpen-source Agent Development Environment (ADE) for running Claude Code, Codex, OpenCode and other coding agents side by side in isolated worktrees.
- PaseoSelf-hosted control plane for Claude Code, Codex, Copilot, OpenCode, and Pi. Desktop, mobile, and web clients. Apache 2.0.
- PiMinimal MIT terminal coding agent by Mario Zechner. Thin tool surface, extensions, multi-provider models; you pay only for API usage.
- PlandexTerminal-based AI coding agent designed for large, multi-step tasks. Plans and executes across dozens of files with up to 2M tokens of context, MIT licensed.
- Prime AgentPrimeIntellect's self-improving coding agent built on a Recursive Language Model (RLM). A persistent IPython kernel as its single tool, a /refine command that lets it improve its own prompts, skills, and memory.
- QoderAlibaba's AI IDE. Recurring seats: Lite $10, Pro $20, Pro+ $60, Ultra $200. Usage is Auto credits.
- QuotiomacOS menu-bar quota switcher. Free app; not a paid command-center SaaS.
- Qwen CodeAlibaba open CLI. ModelStudio Coding Plan / Token Plan / API; Qwen OAuth ended 2026-04-15.
- Replit AgentReplit Agent 4 builds apps, sites, decks, and mobile from plain language on a hosted workspace, with a visual canvas and parallel agents.
- ripwireripwire is Red Hat's Apache-2.0 CLI and MCP server that hands a coding agent a ranked call graph, so it reads fewer files and spends fewer tokens.
- Rovo DevAtlassian coding agent. CLI is acli rovodev. Not free on trial.
- sctxxsctxx is an Apache-2.0 Rust CLI that folds Claude Code, Codex, or Pi transcripts into a verified handoff for another coding agent.
- SerenaMCP toolkit that gives coding agents IDE-level semantic code retrieval, editing, refactoring, and debugging through symbol-level tools.
- SessionMartMetered, pay-as-you-go coding agent platform: one app for Claude Code, Codex, and Kimi Code sessions with transparent rates, hard budget caps, and $5 free credit on signup.
- SkillsyncSkillsync is a local-first Mac app and CLI that moves AI coding sessions across Claude Code, Codex, Cursor, and OpenCode.
- Spec KitAn open-source Spec-Driven Development toolkit that makes specifications executable. Works with Claude Code, GitHub Copilot, Gemini CLI, and Codex to keep agents on task.
- SpecboardSpec and context management for AI coding agents. A 4-stage pipeline turns ideas into specs, a mind map and Markdown editor structure them, and a native MCP server lets agents read and write specs directly.
- T3 CodeOpen-source agent harness control surface for Claude Code, Codex, Cursor, Grok Build, and OpenCode with desktop, web, and mobile apps.
- TabnineAI code completion and chat. Not a 2024 Atom/Sublime blurb.
- TermanyTermany is an AGPL-3.0 agent-native terminal that keeps many coding-agent sessions, Bots, diffs, worktrees, and token cost in one window.
- TortieCalm open-source agent multiplexer for macOS that runs coding-agent sessions in tmux inside a familiar IDE-style window.
- TRAEByteDance's AI IDE. Recurring seats: Lite $3, Pro $10, Pro+ $30, Ultra $100. Usage is billed in dollars, not extra-fast request packs.
- TTY.BuildTTY.Build is an MIT iPhone and Mac app that reaches coding-agent terminals on your computer over an end-to-end encrypted relay.
- v0Vercel UI generator. Credits, not unmetered codegen.
- WakuWaku is a fast native macOS app by egoist (ChatWise) that unifies local AI coding agents like Claude Code, Codex, and OpenCode in one Rust + GPUI interface.
- WindsurfCognition's local AI IDE (Windsurf 2.0 / Devin Desktop). Plan on your machine, one-click handoff to Devin in the cloud, review the PR in the same app.
- YouwareAI-driven full-stack development platform with no-code AI agent building, specialized builders, and instant deployment to turn ideas into working apps.
- ZCodeZCode is Z.ai's official Agentic Development Environment for GLM-5.2: a free desktop app where agents plan, edit, test, and iterate on 1M-token context.
- ZedRust editor from the Atom team. Free to use. Zed Pro is $10/month; Business is $20/user. AI is BYOK or a paid add-on.
- Tencent CodeBuddyTencent coding assistant. No public dollar table;
- Claude Sonnet 4.5Anthropic's previous Sonnet snapshot: 200k context, $3/$15 per 1M tokens. Docs now sell newer Claude 4.6 and Claude 5 lines.
- Claude Opus 5.5Anthropic Claude Opus 5.5: Fable-5.1-level intelligence at $4/$20 per 1M tokens, 1M context, and day-one GitHub Copilot support.
- Claude Opus 5Anthropic's frontier Opus model with 1M-token context and effort-controlled reasoning, near-Fable-5 intelligence at Opus-4.8 pricing for agents and coding.
- DeepSeek-V4.1-FlashDeepSeek-V4.1-Flash is a MIT 552B multimodal MoE with 8B/16B activation, 1M context, and about 1/4 the KV cache of V4-Flash.
- DeepSeek V4 FlashDeepSeek small agent model: 284B/13B MoE, 1M context, MIT weights, $0.14/$0.28 per 1M tokens.
- DeepSeek V4 Pro 0813DeepSeek flagship 1.6T MoE with 49B active, 1M context, MIT weights. API $0.29/$1.20 cached $0.03.
- GLM-4.7An open-source multilingual multimodal chat model from Zhipu AI with advanced thinking capabilities, exceptional coding performance, and enhanced UI generation.
- GLM-5.2Zhipu's June 2026 744B MoE coding model with 1M context and MIT weights. Successor GLM-5.3 is now the flagship.
- GLM-5.3-FlashZhipu's first natively multimodal GLM (confirmed as the 'Ox Alpha' stealth model): 320B MoE with 18B active, 1M context, MIT open weights at $0.15/M input.
- GLM-5.3Zhipu coding model on GLM Coding Plan. Token API not on the public table yet. Not $18-only.
- GPT-6 LunaOpenAI GPT-6 Luna: the cheapest GPT-6 tier at $0.10/$0.50 per 1M tokens with a 1.05M context window and max-effort reasoning.
- GPT-6 SolOpenAI GPT-6 Sol: 1.05M context, reasoning up to max effort and $2/$10 per 1M tokens, with day-one GitHub Copilot support.
- Grok 4.6SpaceXAI's frontier 1.5T reasoning model with 500K-token context, agentic coding strength, and real-time X data at roughly half the price of rivals.
- Grok 4.7SpaceXAI's Grok 4.7 flagship for coding and agents: 500K context, $1.60/$4.80 per 1M tokens, 46.4 on the Artificial Analysis index.
- KAT-Coder V2.5Kwaipilot's open-weight agentic coding model: 35B MoE, 3B active per token, Qwen3.6 base, Apache 2.0, 262K context, top PinchBench tool-use score.
- Laguna S 2.1Poolside's open-weight 118B MoE coding model with 8B active parameters, a 1M-token context window, native interleaved reasoning, and an OpenMDW-1.1 license.
- LongCat 2.0Meituan's open-weight MoE model: 1.6T total / ~48B active params, 1M context, MIT. Strong on coding and agentic tasks (2026-08-25).
- CodeLlama 34B InstructPrevious Code Llama 34B Instruct snapshot. Not a 2026 coding default.
- MiniMax M2.1Open-source 230B parameter MoE model optimized for multi-language coding, agentic workflows, and real-world development tasks with 74% SWE-bench performance.
- MiniMax M3MiniMax open-weight frontier model (June 1, 2026): 1M-token MSA context, native image/video input, desktop computer use, and discounted API pricing.
- Muse GlimmerMeta's open-weight 30B agentic multimodal model distilled from Muse Spark, designed to run always-on coding and tool-use agents locally on a single consumer.
- Muse Spark 1.2Meta's coding-focused flagship model powering Muse Code: 1M context, higher first-attempt accuracy, reliable tool calling, and end-to-end developer workflows.
- Nex-N2.5-miniNex-N2.5-mini is Nex-AGI's Apache-2.0 multimodal agent model for computer use, browsing, and coding.
- Nex-N2.5-ProNex-N2.5-Pro is Nex-AGI's Apache-2.0 multimodal agent checkpoint for computer use, browsing, and coding.
- Qwen2.5-Coder-32BPrevious Qwen code snapshot.
- Qwen3.8-Flash-NextAlibaba's open-weight architecture preview of Qwen4: 125B multimodal MoE with 6B active plus a 51B N-gram table, 262K native context, at $0.16/M input.
- Tiel-Coder 35B A3BAgentic coding MoE. Not a lab release.
- Agent DispatcherAgent Dispatcher is an MIT Claude Code and Codex pack that routes each task to a specialist role with a small skill and tool stack.
- CavemanCaveman is a coding-agent skill and local proxy that shortens agent prose and compresses logs so you spend fewer tokens.
- Open StepsOpen Steps is an MIT Claude Code skill pack that translates agent jargon into plain-language verdicts and next steps.
- PonytailOpen-source agent skill that makes Claude Code, Codex, OpenCode and more write only what the task needs: about 54% less code with the same safety guards.
- Skills For Real EngineersMatt Pocock's composable agent skills for real engineering: grilling, wayfinder, TDD, and code review. MIT. Claude Code and Codex.
- unlazyunlazy is an MIT Claude Code and Codex skill that forces substantial agent work through a Depth Tree of runnable acceptance gates.
All Tags
Items tagged with Coding Agent (131)
Month Visit15900000DR: 95AS: 94
Month Visit12000000DR: 88AS: 90
Month Visit5000000DR: 98AS: 99
Month Visit2500000DR: 92AS: 95
Month Visit2000000DR: 82AS: 80
Month Visit1748000DR: 75AS: 78
Month Visit1567DR: 96AS: 95
Month Visit1000DR: 80AS: 80
Month Visit400000000DR: 88AS: 78
Month Visit45000000DR: 95AS: 88
Month Visit45000000DR: 95AS: 88
Month Visit15000000DR: 95AS: 95
Month Visit15000000DR: 95AS: 95
Month Visit13900000DR: 65AS: 72
Month Visit13770000DR: 77AS: 75
Month Visit12000000DR: 88AS: 90
Month Visit5000000DR: 95AS: 92
Month Visit5000000DR: 88AS: 90
Month Visit5000000DR: 88AS: 90
Month Visit5000000DR: 88AS: 86
Month Visit3000000DR: 98AS: 95
Month Visit2500000DR: 92AS: 95
Month Visit2500000DR: 92AS: 95
Month Visit2500000DR: 70AS: 60