Claude Code

Anthropic's agentic coding tool for the terminal, IDE and web. New in v2.1.314 (Oct 30, 2026): a permissions.blockWritesOutsideWorkingDirectories setting makes Write, Edit and NotebookEdit refuse any path outside your working directories in every permission mode. v2.1.316 (Oct 31) adds CLAUDE_CODE_DISABLE_ULTRATHINK and CLAUDE_CODE_SUBAGENT_EFFORT settings. v2.1.317 (Nov 3) asks before a web or shell tool call sends your account email address to the network. v2.1.319 (Nov 6) adds a permissions.denyInsteadOfPrompting setting that denies a tool call that would wait on a permission prompt and lets the turn continue, and moves MCP tasks to the background right away. v2.1.321 (Nov 9) adds Claude Fable 5.2 as the default Fable model and fixes several security issues, including MCP OAuth requests sending secrets such as refresh tokens to another host when a server redirected them, and a case where a read-only Bash command ran outside the sandbox without a permission prompt; v2.1.322 (Nov 9) adds fast mode on Vertex. v2.1.323 (Nov 12, 2026) adds Code Mode, an experimental opt-in where Claude writes JavaScript to call its tools (admins can turn it off for an organization), an engines field in plugin.json so plugins outside their stated Claude Code version range are not installed or loaded, a startup warning for Bash allow rules with a * in a variable's value, and in VS Code a trust prompt before the first session in a folder you have not trusted. v2.1.325 (Nov 13) fixes a security issue in how zstd-compressed responses are decoded, tells you how to continue (/rewind or /clear) when your organization's policy blocks a request, and fixes /security-review failing in worktrees of bare repositories and in --separate-git-dir checkouts.

checked 11/15
Category
Coding & Vibe Coding
Price
Included with paid Claude plans
Free option
No
Last checked
Nov 15, 2026

agentterminalcli

Visit Claude Code ↗

Get the weekly dropThe best new AI tools, one email a week. Free.

Related Coding & Vibe Coding tools 26

See all
Tool
Price
Status
Link
CursorAI-first code editor with agent mode, codebase chat and tab completion. Now sold as part of The X Subscription (Oct 13, 2026); existing Cursor plans keep working as legacy plans. The Cursor Agent SDK (announced Oct 20, 2026, GA in v0.3.0 on Oct 23) lets you write your own agents as code, with prompts in Markdown and tools as TypeScript functions, built-in evals and a local playground, then deploy them to Cursor or self-host them in a container; it is the framework behind Cursor's own Bugbot and Security Review. DeepSeek V4.1 Flash, an open-weight model with a 1M-token context, was added Oct 26 and is billed as a third-party model. New Nov 5, 2026: Build Live Apps (Cursor Apps). On paid plans with cloud agents, a cloud agent can scaffold a web app, provision Postgres when needed, put team apps behind Cursor SSO, run security checks and publish a live URL you share with teammates (or publicly on individual plans). Deploy from a new Cursor Origin repo or an existing GitHub repo; nothing goes live until checks pass and you explicitly publish. New Nov 10, 2026: Projects, Cursor's workspace for directing a fleet of agents through one coordinator, is now multiplayer (beta, rolling out to all users). Invite teammates into a Project to share requirements docs, specs and mockups as context every agent can read, track who and which agent is doing what on a shared task board, and let teammates' coordinator agents plan around each other's work.
Price Plus from $8/mo (Grok models only); Premium $30/mo adds cloud agents and third-party models at API list price
FREE TIERchecked 11/15
Bolt.newPrompt, run, edit and deploy full-stack web apps right in your browser.Affiliate link: we may earn a commission if you sign up, at no extra cost to you.
Price Pro from $25/mo
FREE TIERAFFILIATEchecked 11/15
v0Vercel's AI app builder that turns prompts into React/Next.js apps and UI.
Price Plus from $30/mo
FREE TIERchecked 11/15
LovableBuild full-stack web apps by chatting with an AI engineer. New Oct 20, 2026: Lovable can create a Supabase project for an app with no backend (you pick the organization and region, and Supabase bills your own organization), and companies with several Lovable workspaces can group them into one organization with shared SSO and SCIM. Also Oct 20: n8n and LlamaParse connectors, plus ByteDance's Seedream 5 Pro image model and Seedance 2.5 video model for app features (an admin enables ByteDance in Connectors first).
Price Pro from $25/mo ($21/mo billed annually); free plan has 5 daily credits
FREE TIERchecked 11/15
FlutterFlowAI-native builder for native iOS and Android apps. Describe the app and an agent builds it, then you refine in threads and push changes yourself (the agent never publishes on its own). Backend, auth, analytics and App Store / Google Play deployment are built in. The visual builder continues as FlutterFlow Studio (AI Agent Panel with your own Claude, Codex, Antigravity or Gemini account, MCP server, Generate with Designer and Test Pilot). FlutterFlow says 3.3M people have built on the platform and 50,000+ apps have shipped. AI-native experience launched Nov 4, 2026; one subscription covers FlutterFlow and Studio.
Price Free plan with a one-time AI allowance; Basic from $39/mo ($29/mo billed yearly); Pro $80/mo ($60/mo yearly); Max $150/mo ($113/mo yearly)
FREE TIERchecked 11/15
ReplitBrowser IDE with Replit Agent that builds and deploys apps from a prompt. New Oct 22, 2026: Monitoring Agent, an on-call agent for published apps. Turn on monitoring alerts and Auto-fix and it investigates production issues from your app's logs and metrics, attempts and validates a fix and emails you a summary; with the experimental Auto-republish setting it can also publish the fix. Replit hasn't published fix-accuracy numbers.
Price Core from $20/mo ($18/mo billed annually)
FREE TIERchecked 11/15
GitHub CopilotAI pair programmer and coding agent inside VS Code, JetBrains and GitHub. New at GitHub Universe (Oct 28, 2026): Copilot Fusion is generally available. Pick Fusion instead of a model and Copilot routes each step of a task across one or more models (GitHub says Fusion Max scored within two points of Opus 5.5 Max on the Artificial Analysis Coding Agent Index at half the cost; that is GitHub's claim). Also new: a redesigned GitHub Copilot app for issue-to-merge agent work, Copilot projects that run parallel agent sessions across several repos, automations that propose improvements from past runs, and Copilot code review Max, which runs several review agents on different models and merges their findings. GitHub Enterprise customers can now use every Copilot feature without a separate Copilot subscription and pay for the AI credits they use (through GitHub Sales for now). New Nov 10, 2026: Google's Gemini 4 Carbon is generally available in Copilot for Pro+, Max, Business and Enterprise users (gradual rollout), billed at provider list pricing under usage-based billing, in VS Code, Visual Studio, JetBrains, Xcode, Eclipse, Copilot CLI, the coding agent, the Copilot app, github.com and GitHub Mobile. GitHub describes it as built for complex coding, agentic and reasoning tasks with a focus on secure code generation.
Price Pro from $10/mo
FREE TIERchecked 11/15
DevinCognition's coding agents: Devin Desktop (the editor formerly called Windsurf) plus Devin cloud agents. Fusion mode in Devin Desktop and CLI pairs a frontier lead model with a cheaper sidekick; with Opus 5.5 and GPT-6 Luna it scores 68.1 on the Artificial Analysis Coding Agent Index. Pro includes free use of Cognition's own SWE-2 model.
Price Free plan; Pro $20/mo; Max $200/mo; Teams from $80/mo
FREE TIERchecked 11/15
Factory DroidFactory's model-agnostic coding agent, in a desktop app for macOS and Windows, a terminal UI and a TypeScript SDK (@factory/droid-sdk), with cloud and local background agents. Droid 1.0 (Oct 29, 2026) makes Script mode the default on supported models: the model writes a small JavaScript program, run in a sandbox, that makes many tool calls in one request, so raw files and logs stay out of its context. Factory says this cut Droid's cost 15% on Claude Opus 5.5 and that Droid beat other harnesses on its own benchmark runs; those are Factory's numbers.
Price Pro $20/mo; Plus $100/mo; Max $200/mo; Teams $60/mo plus $40/seat
checked 11/15
ZedFast open-source code editor with AI edit predictions, an agent panel and bring-your-own-key support.
Price Pro from $10/mo
FREE TIERchecked 11/15
OpenRouterOne OpenAI-compatible API for 500+ models from 80+ providers, with fallback routing.
Price Pay-as-you-go; 5.5% fee on credit purchases
FREE TIERchecked 11/15
Muse Spark Open (Meta)Meta's open-weight multimodal MoE model (816B total, 42B active, 1M context) built for coding and agent work. Released Oct 15, 2026.
Price Free open weights (Muse Model License); hosted via OpenRouter, Groq, Together and others
FREE TIERchecked 11/15
NVIDIA Nemotron 3.5 BoltNVIDIA's open local model (74B total, 9B active, 256K context) for coding, reasoning, vision and tool use. Fits about 24GB of GPU memory via Ollama, llama.cpp or LM Studio (NVIDIA GPUs; no Apple silicon yet). Released Oct 15, 2026. New Oct 23: Nemotron 3.5 Bolt E4B, a small 4B-effective model (built on Gemma 4 E4B) for fast local voice and device assistants with multi-turn tool use, a conversational mode and switchable reasoning. NVIDIA's 4GB Q4_K_M GGUF used about 3.5-4.3GB of VRAM on an RTX 5070 in its tests; in Ollama it's nemotron-3.5-bolt:e4b (7.2-7.9GB download with image input, plus MLX builds for Apple silicon).
Price Free open weights (OpenMDW License 1.1)
FREE TIERchecked 11/15
OpenCodeOpen-source AI coding agent for the terminal, desktop app and IDE. Use its free included models, connect 75+ providers (including local models), or sign in with GitHub Copilot or ChatGPT Plus/Pro. Security note: on Oct 17, 2026 OpenCode disclosed a breach of a legacy system behind its hosted Console that may have exposed provider API keys saved in Console workspaces (1.4% of Console users, all notified by email). Keys you add locally in the CLI or desktop app weren't part of it. Since then Anthropic has revoked affected Claude keys, Google has blocked exposed Gemini keys, OpenAI has refunded API credits used in the attack and OpenCode says its own refunds are underway. If you were notified, replace those keys and check usage back to Oct 16. OpenCode 2.0 (announced Oct 12) runs one shared background service for the terminal, web and desktop apps, with a rebuilt API and background subagents. It ships as a separate package (@opencode/cli); the default install still gives you 1.x, and V1 plugins don't work on 2.0.
Price Open source (MIT); optional Zen pay-as-you-go models
FREEchecked 11/15
Recursive FlintRecursive's first model: an open-weight mixture-of-experts coding model (39.8B total, about 2.5B active per token) built for fast agentic coding on your own machine. Recursive says it leads MoE models under 50B parameters on SWE-Bench Pro v2, Terminal-Bench 2.1 and SWE-Bench Verified, and runs at 125+ tokens/sec on an M4 Pro MacBook Pro. Runs via Ollama (flint:40b), llama.cpp, LM Studio, Unsloth, vLLM or SGLang; the INT4 GGUF needs a 48GB Apple Silicon Mac and Unsloth's 3-bit GGUF fits 24GB RAM. Released Oct 21, 2026; Recursive says it may need more step-by-step guidance than big closed models.
Price Free open weights (Apache-2.0)
FREE TIERchecked 11/15
MiniMax M3.1 FlashMiniMax's open-weight multimodal mixture-of-experts model (about 428B total, 23B active per token, up to 1M tokens of context) for coding, agentic work, computer use and cybersecurity tasks. Takes text, image and video input. MiniMax's own benchmarks put it at 73.7% on DeepSWE v1.1 and 61.7 on OSWorld 2.0, close to big closed models on several agent tests. Too big for a home PC: MiniMax recommends serving it with SGLang, vLLM or TokenSpeed, or using it through MiniMax Agent and the MiniMax API. New in October 2026.
Price Free open weights (MiniMax Community License: commercial use needs a 'Built with MiniMax M3.1-Flash' credit and a notice to MiniMax; written approval above $20M yearly revenue)
FREE TIERchecked 11/15
Nanbeige4.3-33BOpen-weight 33B dense model from the Nanbeige team, built for agentic coding and office-style agent tasks (tool use, planning, multi-step work), with a thinking mode you can switch off and up to 512K tokens of context. On Nanbeige's own benchmark table it beats Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B on most agent tests (for example 80.9 on Terminal-Bench 2.1 and 65.5 on DeepSWE), though Qwen3.8-27B edges it on SWE-Bench Pro and GDPval. Runs with Transformers, SGLang or vLLM (Nanbeige's server examples use four GPUs); community GGUF quants exist for smaller setups. Released Oct 24, 2026; about 500 likes on Hugging Face in its first two days.
Price Free open weights (Apache-2.0)
FREE TIERchecked 11/15
Hugging FaceThe hub for open models, datasets and Spaces demos, plus hosted inference.
Price PRO from $9/mo
FREE TIERchecked 11/15
Modern Web GuidanceFree, open-source (Apache-2.0) agent skill and CLI that feeds your coding agent current web-platform best practices so it stops writing 2019-style JavaScript: native dialogs and popovers, CSS anchor positioning, container queries, view transitions, field-sizing, INP performance fixes, accessibility patterns, passkeys and Chrome's built-in AI APIs, each with browser-compatibility guidance and lightweight fallbacks. Stewarded by the Google Chrome, Microsoft Edge, Mozilla Firefox and MDN teams. Install with npx modern-web-guidance@latest install (or npx skills add / gh skill install GoogleChrome/modern-web-guidance); it works with any coding agent that supports skills (Claude Code, Codex, Gemini CLI, Copilot and others). The CLI searches 200+ expert-reviewed guides offline (no API keys, no network calls for search), and the new legacy-scan command looks through your code for old patterns your agent can modernize. The Chrome team reports agents passing 92% of its 200-task eval with the skill versus 55% without (the team's own eval). The Show HN post runs its commands with DISABLE_TELEMETRY=1, so set that if you don't want usage telemetry. The 1.0 stable release was announced Nov 10, 2026 (preview since Google I/O in May); about 3,770 GitHub stars and a Show HN near 380 points.
Price Free and open source (Apache-2.0)
FREE TIERchecked 11/15
OpenAI CodexOpenAI's coding agent for the CLI, IDE and cloud tasks. GPT-6.1 Terra (released Oct 26, 2026) is available in Codex and ChatGPT Work for Plus, Pro, Enterprise and Edu users; OpenAI says the same usage allowance covers more tasks with Terra than with GPT-6.1 Sol or GPT-6 Astra. In the API it is gpt-6.1-terra at $1 per million input tokens and $5 per million output tokens. Codex CLI 0.169.0 (Nov 13, 2026) keeps project configuration and MCP servers disabled for codex exec in untrusted directories, even with --sandbox workspace-write (pass --trust to save project trust), lets you add or edit custom model providers from the terminal, adds multiple side-chat tabs in the opt-in terminal workspace and fixes Windows sandbox handling for quoted cmd.exe paths.
Price Included with ChatGPT plans (limited on Free and Go)
FREE TIERchecked 11/15
WarpAgentic terminal and development environment with built-in AI agents.
Price Build from $20/mo
FREE TIERchecked 11/15
ClineOpen-source autonomous coding agent for VS Code.
Price Open source
FREEchecked 11/15
OrcaFree, open-source (MIT) desktop app from Stably AI (Y Combinator) for running several coding agents in parallel, each in its own git worktree. Bring the CLI agents and subscriptions you already have (Claude Code, Codex, Gemini, GitHub Copilot, OpenCode, Cline, Grok and any other terminal agent), use each in a chat view or the raw terminal, and review diffs, leave line notes and send PR review comments or failing checks back to an agent. A coordinator agent can split a big task across worker agents; workspaces can run locally, on an SSH host or a cloud VM, and an iOS and Android companion app pings you when an agent needs input. Prompts go straight to the providers you configure. Builds for macOS, Windows and Linux. About 119,000 GitHub stars; ships almost daily (v1.4.252 on Nov 6, 2026 added chat forking and Plan mode).
Price Free and open source (MIT); Enterprise rollout by contact
FREE TIERchecked 11/15
AiderOpen-source AI pair programming in your terminal, with git integration.
Price Open source
FREEchecked 11/15
Qwen CodeOpen-source (Apache-2.0) AI coding agent from Alibaba's Qwen team for the terminal, with IDE plugins (VS Code, Zed, JetBrains), a desktop app, a web UI, SDKs and chat integrations. It has memory, skills, subagents, agent teams and MCP support, and talks to OpenAI, Anthropic, Gemini and Qwen APIs, any compatible third-party provider or a local model in Ollama or vLLM, switchable at runtime. Sign in with a Qwen account or bring your own API key. Install with the standalone script, npm (Node.js 22+) or Homebrew. Qwen Code 1.0 Preview (tagged Nov 11, 2026; preview.1 on Nov 12) merges the agent harness of Alibaba's Qoder with Qwen Code and ships native packages for macOS, Linux and Windows with no separate Node.js install; interfaces and settings may still change during the preview. The stable line is v0.27.3 (Nov 13). v0.27.4 (Nov 15, 2026) makes Auto Mode ask for explicit authorization before risky actions and visibly mark Full Access, restores the /memory controls in the CLI, lets managed agent sessions use local folders you grant without saving credentials or paths, adds Feishu and WeCom webhook output and patches vulnerable dependencies (MCP, DOMPurify and compressed-request parsing). About 30,500 GitHub stars.
Price Free and open source (Apache-2.0); bring your own API key or use a Qwen account
FREE TIERchecked 11/15
Foundry Local (Microsoft)Microsoft's on-device AI runtime and SDKs (C, C++, C#, JavaScript, Python, Rust) for shipping chat, tool calling and audio transcription inside your own apps with no Azure subscription, no API key and no per-token cloud bill. A ~20 MB runtime bundles with your installer, downloads a hardware-matched model from the Foundry catalog on first run (GPT OSS, Qwen, DeepSeek, Mistral, Phi, Whisper and others), accelerates on NPU, GPU or CPU, and exposes OpenAI-compatible chat and Responses APIs in-process or via an optional local server. Generally available since April 9, 2026; used by GitHub Copilot CLI voice input, Raycast, Foxit and others. SDK is MIT; CLI has separate Microsoft license terms; models keep their own licenses. About 2,640 GitHub stars; v2.3.1 shipped Nov 2, 2026. CUDA/cuDNN must be installed separately when you want NVIDIA GPU acceleration.
Price Free (SDK MIT; CLI under Microsoft Foundry Local license terms; model licenses vary)
FREE TIERchecked 11/15