{"data":{"slug":"mlhher-late-cli","name":"late-cli","tagline":"Orchestrate an entire AI dev team on 5GB VRAM with zero config.","github_url":"https://github.com/mlhher/late-cli","owner":"mlhher","repo":"late-cli","owner_avatar_url":"https://avatars.githubusercontent.com/u/263016422?v=4","primary_language":"Go","stars":431,"forks":45,"topics":["agent","ai-agent","ai-coding-assistant","ai-skills","autonomous-agents","claude-code","coding-agent","deepseek","glm","harness","kimi","llm","llm-orchestration","local-ai","local-llm","long-horizon","long-horizon-agents","mcp","qwen"],"archived":false,"github_pushed_at":"2026-09-17T16:05:16+00:00","maintenance_label":"Very active","stars_delta_30d":29,"url":"https://www.graphcanon.com/tools/mlhher-late-cli","markdown_url":"https://www.graphcanon.com/tools/mlhher-late-cli.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mlhher-late-cli","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mlhher-late-cli","description":"High-performance AI agent for long-horizon tasks. Built on empirical research. 200k+ tokens of work inside a 64k context window.","homepage_url":null,"license":"Other","open_issues":6,"watchers":6,"ai_summary":"Late-cli is a single static binary that enables users to orchestrate multiple AI agents for development tasks without configuration, designed to work within 5GB of VRAM. It supports ephemeral subagents and exact-match diffs across various models including Claude, Gemini, Qwen, among others.","readme_excerpt":"## License\n\nBuilt to create engineering leverage, not to supply free infrastructure for AI startups.\n\n* **Free for Builders:** Use Late freely to write code for any project, including commercial ones. Your generated output is yours.\n* **Commercial Infrastructure:** You may not monetize Late itself. Wrapping the orchestration engine into a paid service requires a commercial agreement. *(Converts to GPLv2 on Feb 21, 2030).*","github_created_at":"2026-02-22T05:00:28+00:00","created_at":"2026-07-15T10:59:37.649767+00:00","updated_at":"2026-09-20T05:03:03.665604+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"auto-config","name":"auto-config"},{"slug":"ephemeral-agents","name":"ephemeral-agents"},{"slug":"llm-support","name":"llm-support"}],"trust":{"provenance":{"is_fork":false,"github_id":1163756223,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:03:01.782Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":2,"last_release_at":"2026-09-13T23:06:59Z","stars_delta_30d":29,"open_issues_delta_30d":1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":21,"high_count":0,"last_scan_at":"2026-08-09T04:00:51.543Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:03:02.827Z"},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-09-20T05:03:02.827Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T05:03:02.827Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Projects needing coordination among various AI models like Claude, Gemini, Qwen without heavy setup","Scenarios where limited VRAM capacity, such as 5GB, still requires robust AI orchestration"],"when_not_to_use":["Situations requiring configuration customization to adapt to different project requirements","Workflows that need more than 5GB of VRAM for AI model operations and management"],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:10:22.850Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Orchestrate multiple AI agents for dev tasks without config within 5GB VRAM limit"}]}}