AgentSidekick

CLI Coding Agents

Coding agents that run in the terminal. As of 2026-11-21, 24 indexed products offer it (14 with full profiles), in 9 forms: 8 MCP servers, 5 Rules packs, 3 Platforms, 2 Agent projects. 1 were published in the last 90 days, against 5 in the 90 days before. Gemini CLI has the most GitHub stars, 44% of the total across 23 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 8 indexed · 4 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

CLI Coding Agents: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.DeusData49ktoday
2ai-code-interface.elUnified Emacs interface supporting OpenAI Codex, Antigravity CLI, Claude Code, Pi agent, Muse Code, and moretninja3041d ago
3codex-poolerThe full featured self-hosted Codex gateway, for teams, agents and youicoretech244today
4Yana-AIYana AI 🐰 One Runtime. Any AI. Human-Governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute.AI can act. But who decides how far it goes?Horonomos-laps132d ago

Rules packs 5 indexed · 0 profiled

No compatibility evidence is collected for this form.

5 indexed, none with a full profile yet.

Platforms 3 indexed · 3 profiled

No compatibility evidence is collected for this form.

CLI Coding Agents: Platforms by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Gemini 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.google109ktoday
2AiderOpen-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.Aider-AI (Paul Gauthier)50k6mo ago
3Qwen 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.Alibaba (Qwen team)31ktoday

Agent projects 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

CLI Coding Agents: Agent projects by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1little-coderA harness optimized to smaller LLMsitayinbarr2.7k2mo ago
2easy-agentProduction-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.ConardLi1.0ktoday

Frameworks 2 indexed · 1 profiled

No compatibility evidence is collected for this form.

CLI Coding Agents: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1agent-design-patternsA 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.huangjia20193523d ago

Agent skills 1 indexed · 1 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

CLI Coding Agents: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1PaperOrchestraAn automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.Ar9av76717d ago

IDE extensions 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

CLI Coding Agents: IDE extensions by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1DeepSweep: AI Agent Security & Code ReviewSecurity review for AI coding agents: AI agent security, vulnerability detection and secrets review, locally. Your AI agents have shell access, repo write permissions, and your credentials. DeepSweep reads your agents' settings and MCP configs. It shows agents allowed to run any shell or terminal command, or to git push, deploy or npm publish, without asking you. It shows access beyond the project, such as the whole disk, your home folder or no sandbox. It flags MCP servers whose npm or PyPI package is not pinned to a version or that reach a remote server with no sign-in, and credentials written in plain text into agent configs. The agent environment review runs in under a second. DeepSweep also reviews the code your agent writes for security vulnerabilities and secrets, and records what it found in a local report you can export. Runs in VS Code and agentic IDEs: Antigravity, Trae, Devin Desktop (formerly Windsurf) and Kiro, and in Cursor when installed from the VSIX, alongside extensions and terminal agents: Claude Code, OpenAI Codex, GitHub Copilot, Gemini Code Assist, Cline, Tabnine, Amazon Q Developer and Aider. Run your first review free. No account required.deepsweep-ai——

Infrastructure 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

CLI Coding Agents: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1clawmetrySee your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.vivekchand437today

Plugins 1 indexed · 1 profiled

1 of these are Claude plugins, which Claude Code documents (protocol-level). DER

CLI Coding Agents: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1plan-cascadeAI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).Taoidle1348mo ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
GitHub14.2%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
terminal coding agent3
cli coding agent0
claude codeIgnored
codex cliIgnored
gemini cliIgnored
aider21
opencodeIgnored

Segment statistics

Whole catalogue (24 indexed products). Calculated 2026-11-21.

24DERIndexed products14 with full profiles
1DERLaunched, last 90 days5 in the 90 days before
1DERMomentum vs catalogue50 = same pace as the catalogue
44%DERLargest project's share of starsAcross 23 products with their own repository
0.295DERConcentration (HHI)About 3 equal-sized projects’ worth; highly concentrated
134SRCMedian starsPer product with its own repository
79%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.295 means stars are spread as if across about 3 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: CLI Coding Agents: score 62.5 HEU, competition High, confidence Low. Only 24 indexed products match "CLI Coding Agents", against 481 in Coding Agent CLIs & Extensions overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .