Coding Agent CLIs & Extensions
Terminal agents, IDE extensions, skills and plugins for coding assistants. As of 2026-11-21, 481 indexed products match this subcategory (193 with full profiles); 250 were published in the last 90 days, against 46 in the 90 days before, faster than the catalogue as a whole. By GitHub stars, Codex leads, holding 15% of the stars of the 457 products here with their own repository. The most common form is MCP servers (60% of indexed products).
SubcategorySegment label: Outpacing the catalogue DER
Segment statistics
Whole catalogue (all 481 indexed products, not only profiled ones). Calculated 2026-11-21.
Outpacing the catalogue. Mid-sized for its level, with launches growing faster than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.069, attention is spread as if across about 14 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 287 | 59.7% | 44 |
| Plugins | 70 | 14.6% | 38 |
| Agent skills | 41 | 8.5% | 40 |
| IDE extensions | 35 | 7.3% | 36 |
| Rules packs | 21 | 4.4% | 9 |
| Platforms | 11 | 2.3% | 11 |
| Agent projects | 6 | 1.2% | 6 |
| Frameworks | 5 | 1.0% | 4 |
| Infrastructure | 3 | 0.62% | 3 |
| Agent SDKs | 1 | 0.21% | 1 |
| Developer tools | 1 | 0.21% | 1 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| IDE ExtensionsAI assistants delivered as editor extensions. | 291 | 72 | 201 | Crowded, outpacing the catalogue |
| Agent Skills & PluginsReusable skills, slash commands, hooks and subagents for coding agents. | 155 | 101 | 45 | Established |
| CLI Coding AgentsCoding agents that run in the terminal. | 24 | 14 | 1 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (193 of 481), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | CodexOpenAI's software engineering agent that reads, edits and runs code locally (CLI, IDE extension, ChatGPT desktop app) or in isolated cloud workspaces (Codex Cloud), and can be driven from GitHub, Slack, Linear or an SDK. | Platform | openai | 136k | today | Apache-2.0 | ||
| 2 | Gemini CLIOpen-source terminal coding agent powered by Gemini models, extensible through MCP servers, extension packages, Agent Skills, hooks, subagents, custom commands and GEMINI.md context files. | Platform | 109k | today | Apache-2.0 | |||
| 3 | deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. | Agent project | bytedance | 86k | today | MIT | ||
| 4 | ClineOpen-source autonomous coding agent available as a VS Code extension, JetBrains plugin, CLI, desktop app and SDK, that plans and executes file edits and terminal commands with user approval using any model provider. | Platform | Cline Bot Inc. | 72k | today | Apache-2.0 | ||
| 5 | gooseOpen-source, local general-purpose AI agent (desktop app and CLI) for coding, research, writing and automation that works with any LLM and is extended through MCP extensions, YAML recipes and subagents. | Platform | Agentic AI Foundation (originally Block) | 57k | 1d ago | Apache-2.0 | ||
| 6 | AiderOpen-source terminal pair-programming tool that edits code in a local git repo, auto-commits changes, maps the repository for context, and works with most LLMs via the user's own API keys. | Platform | Aider-AI (Paul Gauthier) | 50k | 6mo ago | Apache-2.0 | ||
| 7 | Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens. | MCP server | DeusData | 49k | today | MIT | ||
| 8 | agentsPlugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by generators with validation and evals. | Agent skill | wshobson | 43k | 3d ago | MIT | ||
| 9 | context-modeFree, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry. | MCP server | mksglu | 34k | today | — | ||
| 10 | Qwen CodeOpen-source terminal coding agent tuned for Qwen models, with VS Code, Zed and JetBrains integrations, SDKs (TypeScript, Python, Java), a daemon/REST mode, and support for MCP, skills, subagents, extensions, hooks and custom commands. | Platform | Alibaba (Qwen team) | 31k | today | Apache-2.0 | ||
| 11 | Kilo Code: AI Coding Agent, Copilot, and AutocompleteOpen Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands. Features inline autocomplete, browser automation, automated refactoring, and custom modes for planning, coding, and debugging. Supports 500+ AI models including Claude (Anthropic), Gemini, Grok, GPT, Codex and GLM. | IDE extension | kilocode | 28k | today | MIT | ||
| 12 | awesome-claude-code-subagentsA collection of 100+ specialized Claude Code subagents covering a wide range of development use cases | Agent project | VoltAgent | 27k | 19d ago | MIT | ||
| 13 | Roo CodeA whole dev team of AI agents in your editor. | IDE extension | RooVeterinaryInc | 24k | 6mo ago | Apache-2.0 | ||
| 14 | Roo CodeOpen-source VS Code coding agent forked from Cline, known for role-based modes (Code, Architect, Ask, Debug and custom modes); the extension has been shut down. | Platform | Roo Code Inc. | 24k | 6mo ago | Apache-2.0 | ||
| 15 | Roo Code NightlyA whole dev team of AI agents in your editor. | IDE extension | RooVeterinaryInc | 24k | 6mo ago | Apache-2.0 | ||
| 16 | rocketride-serverRocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production. | MCP server | rocketride-org | 20k | today | MIT | ||
| 17 | Claude-BugHunterA Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices. | Agent skill | elementalsouls | 15k | today | MIT | ||
| 18 | Claude ContextMCP server that indexes a codebase into a vector database for semantic code search by coding agents. | Developer tool | Zilliz | 13k | 9d ago | MIT | ||
| 19 | pixel-agentsA playful way to manage your AI workforce | Agent project | pixel-agents-hq | 10k | 1d ago | MIT | ||
| 20 | Claude Agent SDKSDK that exposes the agent loop behind Claude Code (file and shell tools, subagents, hooks, permissions, context compaction) for building custom agents in Python or TypeScript. | SDK | Anthropic | 8.6k | today | MIT | ||
| 21 | awesome-codex-subagentsA collection of 130+ specialized Codex subagents covering a wide range of development use cases. | Agent skill | VoltAgent | 6.5k | 19d ago | MIT | ||
| 22 | Claude Code Workflow StudioVisual Workflow Editor for Claude Code, GitHub Copilot, and more AI agents | IDE extension | breaking-brake | 5.5k | 1mo ago | AGPL-3.0-or-later | ||
| 23 | claude-code-guideClaude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user! | Agent skill | zebbern | 4.7k | today | MIT | ||
| 24 | KiroAWS's agentic development platform that turns prompts into specs and tasks, sharing one agent harness across an IDE, a VS Code extension, a CLI, a web agent, mobile and the Crew personal agent, configured through .kiro steering, hooks, MCP, skills and powers. | Platform | Amazon Web Services | 4.5k | 16d ago | — | ||
| 25 | founder-skillEleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT. | Agent skill | Jakeschincariol | 4.5k | 1mo ago | MIT | ||
| 26 | Continuous-Claude-v3Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. | Agent skill | parcadei | 4.0k | 5d ago | MIT | ||
| 27 | buildwithclaudeA single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw | MCP server | davepoon | 3.8k | 1d ago | MIT | ||
| 28 | cc-sddTurn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity. | Agent skill | gotalab | 3.8k | 1mo ago | MIT | ||
| 29 | Claude-Code-QuestClaude Code guide in three levels, Beginner to Advanced: hands-on lessons with checked exercises, every volatile fact cited to its source. Independent community guide. | Agent skill | wesammustafa | 3.7k | 6d ago | — | ||
| 30 | twinny - AI Code Completion and ChatAI code completion, chat, inline edit and code review on models you run. Private, open source, one gateway for the whole team. | IDE extension | twinnydotdev | 3.7k | 3d ago | MIT | ||
| 31 | gentle-shellGentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD). | Agent skill | Gentleman-Programming | 2.9k | today | MIT | ||
| 32 | little-coderA harness optimized to smaller LLMs | Agent project | itayinbarr | 2.7k | 2mo ago | Apache-2.0 | ||
| 33 | mcphub.nvimAn MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins. | MCP server | ravitemer | 1.8k | 10mo ago | MIT | ||
| 34 | erd-editorDesign database schemas as ERDs in your browser, VS Code, JetBrains IDEs or Obsidian. Import SQL, DBML and GraphQL, export DDL and code, and let coding agents edit live over MCP. | MCP server | dineug | 1.8k | 18d ago | MIT | ||
| 35 | deja-vu — Coding Agent Memory & Session SearchLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | MCP server | vshulcz | 1.6k | today | MIT | ||
| 36 | deja-vuLocal memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor. | MCP server | vshulcz | 1.6k | today | MIT | ||
| 37 | arena-skillWhen Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill. | Agent skill | Jakeschincariol | 1.6k | 1mo ago | MIT | ||
| 38 | evoturns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents. | Agent skill | evo-hq | 1.5k | 3d ago | Apache-2.0 | ||
| 39 | oh-my-agentAgent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates. | Agent skill | first-fluke | 1.5k | 1d ago | MIT | ||
| 40 | SpecStorySave, export, search and share AI chat history from Cursor, VS Code Copilot, Claude Code, Codex, Gemini, OpenCode and more | IDE extension | SpecStory | 1.4k | 1d ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 11 | 2.3% |
| PostgreSQL | 4 | 0.8% |
| WordPress | 3 | 0.6% |
| Azure | 2 | 0.4% |
| Discord | 2 | 0.4% |
| Firebase | 2 | 0.4% |
| GraphQL | 2 | 0.4% |
| Snowflake | 2 | 0.4% |
| Terraform | 2 | 0.4% |
| Xcode / iOS | 2 | 0.4% |
| AWS | 1 | 0.2% |
| Airtable | 1 | 0.2% |
| Confluence | 1 | 0.2% |
| Docker | 1 | 0.2% |
| GitLab | 1 | 0.2% |
Launches per month
New Coding Agent CLIs & Extensions products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 1 |
| 2025-01 | 2 |
| 2025-02 | 4 |
| 2025-03 | 2 |
| 2025-05 | 2 |
| 2025-06 | 5 |
| 2025-07 | 5 |
| 2025-08 | 2 |
| 2025-09 | 4 |
| 2025-10 | 4 |
| 2025-11 | 6 |
| 2025-12 | 4 |
| 2026-01 | 12 |
| 2026-02 | 15 |
| 2026-03 | 20 |
| 2026-04 | 15 |
| 2026-05 | 13 |
| 2026-06 | 13 |
| 2026-07 | 11 |
| 2026-08 | 24 |
| 2026-09 | 177 |
| 2026-10 | 56 |
| 2026-11 | 15 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: CLI Coding AgentsCLI Coding Agents | High | Low | 62.5 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .