Autonomous Coding
Agents that plan and carry out coding tasks end to end with little supervision. As of 2026-11-21, 186 indexed products match this subcategory (115 with full profiles); 63 were published in the last 90 days, against 35 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, Claude Code leads, holding 24% of the stars of the 163 products here with their own repository. The most common form is MCP servers (51% of indexed products).
SubcategorySegment label: Thin DER
Segment statistics
Whole catalogue (all 186 indexed products, not only profiled ones). Calculated 2026-11-21.
Thin. Among the smallest 30% of nodes at its level, and launches are not outpacing the catalogue. 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 0.115, attention is spread as if across about 9 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 | 95 | 51.1% | 44 |
| Plugins | 32 | 17.2% | 19 |
| Agent skills | 26 | 14.0% | 25 |
| IDE extensions | 9 | 4.8% | 7 |
| Agent projects | 7 | 3.8% | 7 |
| Frameworks | 5 | 2.7% | 5 |
| Platforms | 4 | 2.2% | 4 |
| Rules packs | 3 | 1.6% | 1 |
| Infrastructure | 3 | 1.6% | 3 |
| Libraries | 2 | 1.1% | 0 |
4 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 |
|---|---|---|---|---|
| Repository UnderstandingExploring and explaining how an unfamiliar codebase is structured and works. | 40 | 13 | 15 | Thin |
| Feature ImplementationBuilding new features from a spec, plan or natural-language request. | 13 | 12 | 4 | Thin |
| Issue ResolutionTurning bug reports and tickets into working fixes. | 1 | 1 | 1 | Thin |
| Multi-file Code ChangesMaking coordinated edits and refactors across many files of a codebase. | 0 | 0 | 0 | Empty |
Top 40 products by GitHub stars
Search the directoryProfiled products only (115 of 186), 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 | Claude CodeAnthropic's agentic coding tool that reads a codebase, edits files, runs commands and manages git, available as a terminal CLI, VS Code and JetBrains extensions, a desktop app, and cloud sessions on the web and mobile. | Platform | Anthropic | 157k | today | — | ||
| 2 | ClineAutonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way. | IDE extension | saoudrizwan | 72k | today | Apache-2.0 | ||
| 3 | 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 | ||
| 4 | Cline (Nightly)Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way. | IDE extension | saoudrizwan | 72k | today | Apache-2.0 | ||
| 5 | claude-code-best-practicefrom vibe coding to agentic engineering - practice makes claude perfect | Agent skill | shanraisshan | 69k | today | MIT | ||
| 6 | awesome-claude-codeA hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affiliation). A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins | Agent skill | hesreallyhim | 58k | today | — | ||
| 7 | oh-my-claudecodeTeams-first Multi-agent orchestration for Claude Code | Framework | Yeachan-Heo | 41k | today | MIT | ||
| 8 | awesome-claude-skillsA curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code | Agent skill | travisvn | 16k | 6mo ago | — | ||
| 9 | agent-orchestratorPlan, run and supervise fleets of agents from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps. Supports Claude Code, Codex & 35+ coding agents. | Agent project | OrchestratorInc | 15k | today | Apache-2.0 | ||
| 10 | InsForgeThe all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end. | Agent project | InsForge | 13k | 1d ago | Apache-2.0 | ||
| 11 | superpowers-zh🦸 AI 编程超能力 · 中文增强版 — superpowers(250k+ ⭐)完整汉化 + 4 个中国原创 skills,让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活 | Agent skill | jnMetaCode | 8.6k | 5d ago | MIT | ||
| 12 | TokenEconomizerExperience-Driven Black-Box Cost Control for Coding Agents | Agent project | microsoft | 7.9k | 1d ago | MIT | ||
| 13 | Claude Code Ultimate GuideSearch the Claude Code Ultimate Guide and machine-readable references from any MCP client. | MCP server | FlorianBruniaux | 6.5k | 2d ago | CC-BY-SA-4.0 | ||
| 14 | rllmDemocratizing Reinforcement Learning for LLMs | Framework | rllm-org | 5.9k | 1mo ago | Apache-2.0 | ||
| 15 | lean-ctxLeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths. | MCP server | yvgude | 4.0k | 3d ago | Apache-2.0 | ||
| 16 | Vibe-SkillsIntelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE. | Agent skill | foryourhealth111-pixel | 3.8k | 12d ago | Apache-2.0 | ||
| 17 | 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 | — | ||
| 18 | teaql-agent-kitA model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification. | Agent project | teaql | 2.8k | 11d ago | MIT | ||
| 19 | CodeNomadCodeNomad: The command center that puts AI coding on steroids. | Agent project | NeuralNomadsAI | 2.7k | today | MIT | ||
| 20 | gemini-mcp-toolMCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding | MCP server | jamubc | 2.3k | 6d ago | — | ||
| 21 | zerostackLightweight coding agent written in Rust, optimized for memory footprint and performance | Agent project | gi-dellav | 1.8k | 2d ago | GPL-3.0 | ||
| 22 | Concord MCPCross-harness communication and shared work-state for AI coding agents. | MCP server | Get-Concord-AI | 1.5k | 1d ago | MIT | ||
| 23 | ChatGPT - Genie AIYour best AI pair programmer. Save conversations and continue any time. A Visual Studio Code - ChatGPT Integration. Supports GPT-4 Turbo, GPT3.5 Turbo, GPT3 and Codex models. Create new files, view diffs with one click; your copilot to learn code, add tests, find bugs and more. | IDE extension | genieai | 1.3k | 1mo ago | ISC | ||
| 24 | autoprompt-skillAutoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks. | Agent skill | Spielewoy | 1.3k | 1mo ago | MIT | ||
| 25 | Claude-Skills403 AI skills, 76 expert agents, and 973 stdlib Python tools for every team: engineering, UI/UX design, PM, marketing, C-level, compliance, business ops, research, founders, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants. | MCP server | borghei | 1.2k | 13d ago | — | ||
| 26 | CORALOpen-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026. | Framework | Human-Agent-Society | 1.1k | 1mo ago | Apache-2.0 | ||
| 27 | OpenAlpha_EvolveOpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve. | Agent project | shyamsaktawat | 1.1k | 1y ago | MIT | ||
| 28 | sno-stationWhen Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer. | Agent skill | sno-ai | 1.0k | today | Apache-2.0 | ||
| 29 | squadraCoordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits. | MCP server | dagoSte | 984 | 2d ago | MIT | ||
| 30 | sno-station-skillsSno: Smart agents. Senior habits. Better every day. Open-source skills that make Claude Code, Codex, Cursor and Hermes Agent work like a team that has shipped before: review by a different agent, a handover before a usage limit stops the work, "done" proven by a real run, and a nightly loop that learns from your own sessions. | Agent skill | sno-ai | 869 | 1d ago | Apache-2.0 | ||
| 31 | MegaMemoryPersistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer. | MCP server | 0xK3vin | 737 | 6mo ago | MIT | ||
| 32 | super-boardAutonomous GitHub Project build → QA → review loop for Claude Code. One-line install. | Agent skill | EricTechPro | 723 | 22d ago | MIT | ||
| 33 | claude-code-workflowsDevelopment workflows for Claude Code that keep broad exploration focused on the outcome you approved. | Plugin | shinpr | 719 | 1d ago | MIT | ||
| 34 | nWaveAI agents that guide you from idea to working code, with you in control at every step. | Agent skill | nWave-ai | 636 | 2d ago | MIT | ||
| 35 | mcp-pointerMCP tool: let you point at DOM elements for your favorite agentic coding tool. Let AI see what you see. | MCP server | etsd-tech | 599 | 1y ago | MIT | ||
| 36 | the-architectA Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES. | Plugin | Hainrixz | 586 | 27d ago | MIT | ||
| 37 | claude-code-hooksclaude code hooks - adding voice on each hook | Agent skill | shanraisshan | 572 | 5mo ago | MIT | ||
| 38 | smart-ralphSpec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow. | Agent skill | tzachbon | 565 | 24d ago | MIT | ||
| 39 | apexyardYour AI engineering org, governed. Ship agent-built code safely to production. | Agent skill | me2resh | 552 | today | MIT | ||
| 40 | npcshthe composable multi-agent shell | Framework | NPC-Worldwide | 506 | today | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 3 | 1.6% |
| SAP | 2 | 1.1% |
| AWS | 1 | 0.5% |
| Android | 1 | 0.5% |
| Figma | 1 | 0.5% |
| Jira | 1 | 0.5% |
| 1 | 0.5% | |
| Playwright | 1 | 0.5% |
| PostgreSQL | 1 | 0.5% |
Launches per month
New Autonomous Coding products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 1 |
| 2025-01 | 1 |
| 2025-03 | 1 |
| 2025-04 | 1 |
| 2025-05 | 2 |
| 2025-06 | 2 |
| 2025-07 | 3 |
| 2025-08 | 1 |
| 2025-09 | 2 |
| 2025-10 | 4 |
| 2025-11 | 4 |
| 2025-12 | 2 |
| 2026-01 | 7 |
| 2026-02 | 8 |
| 2026-03 | 14 |
| 2026-04 | 6 |
| 2026-05 | 8 |
| 2026-06 | 4 |
| 2026-07 | 15 |
| 2026-08 | 16 |
| 2026-09 | 12 |
| 2026-10 | 33 |
| 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: Multi-file Code ChangesMulti-file Code Changes | Low | Low | 58.0 |
| Coverage gap: Issue ResolutionIssue Resolution | Low | Low | 57.8 |
| Coverage gap: Feature ImplementationFeature Implementation | Medium | Low | 56.2 |
| Coverage gap: Repository UnderstandingRepository Understanding | High | Low | 52.0 |
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 .