--- title: "agent-kit vs learn-claude-code" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keyid-ai-agent-kit-vs-shareai-lab-learn-claude-code" tools: ["keyid-ai-agent-kit", "shareai-lab-learn-claude-code"] --- # agent-kit vs learn-claude-code *GraphCanon updated Jul 11, 2026* ## Verdict Pick agent-kit when agent-kit is primarily JavaScript; learn-claude-code is Python; pick learn-claude-code when learn-claude-code is primarily Python; agent-kit is JavaScript. [agent-kit](https://keyid.ai) reports 686 GitHub stars, 9 forks, and 1 open issues, last pushed Mar 13, 2026. [learn-claude-code](https://learn.shareai.run) has 71k stars, 12k forks, and 62 open issues, last pushed Jun 26, 2026. Figures are from public GitHub metadata via [agent-kit's repository](https://github.com/KeyID-AI/agent-kit) and [learn-claude-code's repository](https://github.com/shareAI-lab/learn-claude-code). | | [agent-kit](/tools/keyid-ai-agent-kit.md) | [learn-claude-code](/tools/shareai-lab-learn-claude-code.md) | | --- | --- | --- | | Tagline | Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup. | Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 | | Stars | 686 | 70,653 | | Forks | 9 | 11,506 | | Open issues | 1 | 62 | | Language | JavaScript | Python | | Adopt for | - | Learn-Claude-Code is a minimalistic development tool leveraging Bash and Python to build an agent harness inspired by Claude coding concepts. | | Persona | - | - | | Runtime | - | - | | License | - | MIT License | | Categories | AI Agents, Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-kit](/tools/keyid-ai-agent-kit.md) | [learn-claude-code](/tools/shareai-lab-learn-claude-code.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Active (82%) | | Days since push | 120d | 14d | | Open issues (now) | 1 | 62 | | Security scan | No MCP manifest | No lockfile | | Full report | [trust report](/tools/keyid-ai-agent-kit/trust.md) | [trust report](/tools/shareai-lab-learn-claude-code/trust.md) | ## Decision facts: learn-claude-code - **Requirements:** Min 1 GB RAM - **Adopt for:** Learn-Claude-Code is a minimalistic development tool leveraging Bash and Python to build an agent harness inspired by Claude coding concepts. - **License detail:** MIT License ## Choose when ### Choose agent-kit if… - agent-kit is primarily JavaScript; learn-claude-code is Python. - Tags unique to agent-kit: agent, claude, email, keyid. - Leaner open-issue backlog (1). ### Choose learn-claude-code if… - learn-claude-code is primarily Python; agent-kit is JavaScript. - Requirements: Min 1 GB RAM. - Tags unique to learn-claude-code: agent-development, claude-code, educational, llm. - When you prefer leveraging both Bash scripting and Python for developing AI agents. ## When NOT to use agent-kit - Last GitHub push was 121 days ago (slowing maintenance, Mar 13, 2026). Validate activity before betting a new project on agent-kit. - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ## When NOT to use learn-claude-code - For projects requiring extensive front-end integration with complex UI frameworks as Learn-Claude-Code focuses on backend scripting and Python. - If your project needs a fully-fledged development suite; Learn-Claude-Code offers a more streamlined, educational approach rather than comprehensive feature-rich suites. ## Common questions ### What is the difference between agent-kit and learn-claude-code? agent-kit: Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.. learn-claude-code: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-kit over learn-claude-code? Choose agent-kit over learn-claude-code when agent-kit is primarily JavaScript; learn-claude-code is Python; Tags unique to agent-kit: agent, claude, email, keyid; Leaner open-issue backlog (1). ### When should I choose learn-claude-code over agent-kit? Choose learn-claude-code over agent-kit when learn-claude-code is primarily Python; agent-kit is JavaScript; Requirements: Min 1 GB RAM; Tags unique to learn-claude-code: agent-development, claude-code, educational, llm; When you prefer leveraging both Bash scripting and Python for developing AI agents. ### When should I avoid agent-kit? Last GitHub push was 121 days ago (slowing maintenance, Mar 13, 2026). Validate activity before betting a new project on agent-kit. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ### When should I avoid learn-claude-code? For projects requiring extensive front-end integration with complex UI frameworks as Learn-Claude-Code focuses on backend scripting and Python. If your project needs a fully-fledged development suite; Learn-Claude-Code offers a more streamlined, educational approach rather than comprehensive feature-rich suites. ### Is agent-kit or learn-claude-code more popular on GitHub? learn-claude-code has more GitHub stars (70,653 vs 686). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-kit and learn-claude-code open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to agent-kit or learn-claude-code? GraphCanon lists graph-backed alternatives at [agent-kit alternatives](/tools/keyid-ai-agent-kit/alternatives) and [learn-claude-code alternatives](/tools/shareai-lab-learn-claude-code/alternatives) ([agent-kit markdown twin](/tools/keyid-ai-agent-kit/alternatives.md), [learn-claude-code markdown twin](/tools/shareai-lab-learn-claude-code/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/keyid-ai-agent-kit-vs-shareai-lab-learn-claude-code.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-kit or learn-claude-code? agent-kit: Slowing. learn-claude-code: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agent-kit and learn-claude-code? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-kit trust report](/tools/keyid-ai-agent-kit/trust); [learn-claude-code trust report](/tools/shareai-lab-learn-claude-code/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=keyid-ai-agent-kit`](/api/graphcanon/graph?tool=keyid-ai-agent-kit) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_