[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77J0FW2M1GZ10JRMKZACQCS":3,"skill-same:01M77J0FW2M1GZ10JRMKZACQCS":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M77J0FW2M1GZ10JRMKZACQCS","hedgehog-memory",null,"Radial memory architecture for AI agents — infinite persistent memory with hierarchical compression. Never deletes, only compresses. Origin always in context. pip install hedgehog-memory.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fhedgehog-memory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\r\nname: hedgehog-memory\r\ndescription: Radial memory architecture for AI agents — infinite persistent memory with hierarchical compression. Never deletes, only compresses. Origin always in context. pip install hedgehog-memory.\r\nversion: 0.1.0\r\nmetadata:\r\n  openclaw:\r\n    requires:\r\n      bins:\r\n        - python\r\n    envVars:\r\n      - name: OPENAI_API_KEY\r\n        required: false\r\n        description: OpenAI API key for quality LLM-based summarization. Falls back to built-in keyword summarizer if not set.\r\n      - name: HEDGEHOG_MEMORY_PATH\r\n        required: false\r\n        description: Directory to store memory files. Defaults to .\u002Fmemory_store in the working directory.\r\n---\r\n\r\n# HedgehogMemory\r\n\r\nHedgehogMemory gives AI agents **infinite persistent memory** using a radial compression architecture. Memory is organized as Lines of Nodes — each Node stores the same content at 5 abstraction levels (L0–L4). The L0 one-liner of every node is always loaded at session start (~200 tokens total), so the agent always knows what it knows.\r\n\r\n**Key guarantee:** Memory is NEVER deleted. Old context is only compressed into smaller abstractions. The verbatim original is always recoverable at L4.\r\n\r\n## Installation\r\n\r\n```\r\npip install hedgehog-memory\r\npip install \"hedgehog-memory[openai]\"   # with OpenAI summarizer (recommended)\r\n```\r\n\r\n## Abstraction Levels\r\n\r\n| Level | Max length | Use case |\r\n|-------|-----------|----------|\r\n| L0 | 80 chars | One-liner, always in context |\r\n| L1 | 200 chars | Navigation preview |\r\n| L2 | 600 chars | Detailed summary |\r\n| L3 | 1800 chars | Full context summary |\r\n| L4 | unlimited | Verbatim original |\r\n\r\n## Quick Start\r\n\r\n```python\r\nfrom radial_memory import ContextWindowManager\r\nimport os\r\n\r\nmgr = ContextWindowManager(\r\n    base_path=os.environ.get(\"HEDGEHOG_MEMORY_PATH\", \".\u002Fmemory_store\")\r\n)\r\n\r\n# SESSION START: get ~200-token origin overview (all L0 summaries)\r\noverview = mgr.reset()\r\nprint(overview)  # inject this into your system prompt\r\n\r\n# LOAD: find relevant past context by query\r\nresult = mgr.load(\"Python async patterns\")\r\nif result.found:\r\n    print(result.content)   # L1 summary by default\r\n    result = result.drill_deeper()     # go to L2\r\n    full = result.load_full_state()    # get verbatim original (L4)\r\n\r\n# COMMIT: save current session to memory\r\nmgr.commit(\r\n    topic=\"Async Python debugging session\",\r\n    full_context=\"Complete session transcript goes here...\",\r\n    tags=[\"python\", \"async\", \"debugging\"]\r\n)\r\n```\r\n\r\n## With OpenAI Summarizer (recommended for quality)\r\n\r\n```python\r\nfrom radial_memory import ContextWindowManager\r\nfrom radial_memory.summarizer import OpenAISummarizer\r\nimport os\r\n\r\nsummarizer = OpenAISummarizer(\r\n    api_key=os.environ[\"OPENAI_API_KEY\"],\r\n    model=\"gpt-4o-mini\"\r\n)\r\nmgr = ContextWindowManager(\r\n    base_path=os.environ.get(\"HEDGEHOG_MEMORY_PATH\", \".\u002Fmemory_store\"),\r\n    summarizer=summarizer\r\n)\r\n```\r\n\r\n## Agent Workflow Pattern\r\n\r\nApply this pattern every session:\r\n\r\n```python\r\n# 1. SESSION START\r\noverview = mgr.reset()\r\n# overview = all L0 one-liners for every stored node (~200 tokens)\r\n# Inject overview into your system prompt \u002F context window\r\n\r\n# 2. QUERY - find relevant past context\r\nresult = mgr.load(query=user_request)\r\nif result.found:\r\n    context = result.content  # L1 summary, ~200 chars\r\n    # Need more detail?\r\n    result = result.drill_deeper()   # L2, ~600 chars\r\n    result = result.drill_deeper()   # L3, ~1800 chars\r\n    full = result.load_full_state()  # L4, verbatim original\r\n\r\n# 3. WORK - perform task with full context available\r\n\r\n# 4. COMMIT - persist session to memory\r\nmgr.commit(\r\n    topic=\"Brief description of this session\",\r\n    full_context=full_session_log,\r\n    tags=[\"topic1\", \"topic2\"]\r\n)\r\n```\r\n\r\n## Status Report\r\n\r\n```python\r\nreport = mgr.status_report()\r\n# Returns: total lines, total nodes, last commit timestamp\r\nprint(report)\r\n```\r\n\r\n## Design Principles\r\n\r\n- **Never deletes** — only compresses. The verbatim original is always recoverable.\r\n- **Origin always in context** — L0 summaries of all nodes load at session start (~200 tokens).\r\n- **Radial navigation** — query finds the most relevant node by keyword overlap, then drill deeper on demand.\r\n- **Pluggable summarizer** — swap OpenAI \u002F LiteLLM \u002F custom backends without changing your workflow code.\r\n- **Zero mandatory dependencies** — pure Python stdlib. Works out-of-the-box with KeywordSummarizer.\r\n- **Single-file storage** — all memory in one `origin.json`. Atomic writes, no corruption.\r\n\r\n## Source & Docs\r\n\r\n- GitHub: https:\u002F\u002Fgithub.com\u002Fvvxer\u002FHedgehogMemory\r\n- PyPI: `pip install hedgehog-memory`\r\n- Issues: https:\u002F\u002Fgithub.com\u002Fvvxer\u002FHedgehogMemory\u002Fissues\r\n","# HedgehogMemory\r\n\r\nHedgehogMemory gives AI agents **infinite persistent memory** using a radial compression architecture. Memory is organized as Lines of Nodes — each Node stores the same content at 5 abstraction levels (L0–L4). The L0 one-liner of every node is always loaded at session start (~200 tokens total), so the agent always knows what it knows.\r\n\r\n**Key guarantee:** Memory is NEVER deleted. Old context is only compressed into smaller abstractions. The verbatim original is always recoverable at L4.\r\n\r\n## Installation\r\n\r\n```\r\npip install hedgehog-memory\r\npip install \"hedgehog-memory[openai]\"   # with OpenAI summarizer (recommended)\r\n```\r\n\r\n## Abstraction Levels\r\n\r\n| Level | Max length | Use case |\r\n|-------|-----------|----------|\r\n| L0 | 80 chars | One-liner, always in context |\r\n| L1 | 200 chars | Navigation preview |\r\n| L2 | 600 chars | Detailed summary |\r\n| L3 | 1800 chars | Full context summary |\r\n| L4 | unlimited | Verbatim original |\r\n\r\n## Quick Start\r\n\r\n```python\r\nfrom radial_memory import ContextWindowManager\r\nimport os\r\n\r\nmgr = ContextWindowManager(\r\n    base_path=os.environ.get(\"HEDGEHOG_MEMORY_PATH\", \".\u002Fmemory_store\")\r\n)\r\n\r\n# SESSION START: get ~200-token origin overview (all L0 summaries)\r\noverview = mgr.reset()\r\nprint(overview)  # inject this into your system prompt\r\n\r\n# LOAD: find relevant past context by query\r\nresult = mgr.load(\"Python async patterns\")\r\nif result.found:\r\n    print(result.content)   # L1 summary by default\r\n    result = result.drill_deeper()     # go to L2\r\n    full = result.load_full_state()    # get verbatim original (L4)\r\n\r\n# COMMIT: save current session to memory\r\nmgr.commit(\r\n    topic=\"Async Python debugging session\",\r\n    full_context=\"Complete session transcript goes here...\",\r\n    tags=[\"python\", \"async\", \"debugging\"]\r\n)\r\n```\r\n\r\n## With OpenAI Summarizer (recommended for quality)\r\n\r\n```python\r\nfrom radial_memory import ContextWindowManager\r\nfrom radial_memory.summarizer import OpenAISummarizer\r\nimport os\r\n\r\nsummarizer = OpenAISummarizer(\r\n    api_key=os.environ[\"OPENAI_API_KEY\"],\r\n    model=\"gpt-4o-mini\"\r\n)\r\nmgr = ContextWindowManager(\r\n    base_path=os.environ.get(\"HEDGEHOG_MEMORY_PATH\", \".\u002Fmemory_store\"),\r\n    summarizer=summarizer\r\n)\r\n```\r\n\r\n## Agent Workflow Pattern\r\n\r\nApply this pattern every session:\r\n\r\n```python\r\n# 1. SESSION START\r\noverview = mgr.reset()\r\n# overview = all L0 one-liners for every stored node (~200 tokens)\r\n# Inject overview into your system prompt \u002F context window\r\n\r\n# 2. QUERY - find relevant past context\r\nresult = mgr.load(query=user_request)\r\nif result.found:\r\n    context = result.content  # L1 summary, ~200 chars\r\n    # Need more detail?\r\n    result = result.drill_deeper()   # L2, ~600 chars\r\n    result = result.drill_deeper()   # L3, ~1800 chars\r\n    full = result.load_full_state()  # L4, verbatim original\r\n\r\n# 3. WORK - perform task with full context available\r\n\r\n# 4. COMMIT - persist session to memory\r\nmgr.commit(\r\n    topic=\"Brief description of this session\",\r\n    full_context=full_session_log,\r\n    tags=[\"topic1\", \"topic2\"]\r\n)\r\n```\r\n\r\n## Status Report\r\n\r\n```python\r\nreport = mgr.status_report()\r\n# Returns: total lines, total nodes, last commit timestamp\r\nprint(report)\r\n```\r\n\r\n## Design Principles\r\n\r\n- **Never deletes** — only compresses. The verbatim original is always recoverable.\r\n- **Origin always in context** — L0 summaries of all nodes load at session start (~200 tokens).\r\n- **Radial navigation** — query finds the most relevant node by keyword overlap, then drill deeper on demand.\r\n- **Pluggable summarizer** — swap OpenAI \u002F LiteLLM \u002F custom backends without changing your workflow code.\r\n- **Zero mandatory dependencies** — pure Python stdlib. Works out-of-the-box with KeywordSummarizer.\r\n- **Single-file storage** — all memory in one `origin.json`. Atomic writes, no corruption.\r\n\r\n## Source & Docs\r\n\r\n- GitHub: https:\u002F\u002Fgithub.com\u002Fvvxer\u002FHedgehogMemory\r\n- PyPI: `pip install hedgehog-memory`\r\n- Issues: https:\u002F\u002Fgithub.com\u002Fvvxer\u002FHedgehogMemory\u002Fissues\r\n",{"name":5,"version":24,"metadata":25,"description":7},"0.1.0",{"openclaw":26},{"envVars":27,"requires":34},[28,31],{"name":29,"required":20,"description":30},"OPENAI_API_KEY","OpenAI API key for quality LLM-based summarization. Falls back to built-in keyword summarizer if not set.",{"name":32,"required":20,"description":33},"HEDGEHOG_MEMORY_PATH","Directory to store memory files. Defaults to .\u002Fmemory_store in the working directory.",{"bins":35},[36],"python","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fh\u002Fhedgehog-memory",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill hedgehog-memory",{"tool":52,"command":53},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill hedgehog-memory",{"tool":55,"command":56},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill hedgehog-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fh\u002Fhedgehog-memory\u002FSKILL.md",true,[],[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]