[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7904TPMSJS69T7H37RC70MP":3,"skill-same:01M7904TPMSJS69T7H37RC70MP":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7904TPMSJS69T7H37RC70MP","python-sdk-and-cli",null,"Use the MemMachine Python SDK and CLI for project context, memory add\u002Fsearch\u002Flist\u002Fdelete, semantic profile operations, filters, formatting, config API wrappers, and LangGraph tool helpers.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: python-sdk-and-cli\ndescription: \"Use the MemMachine Python SDK and CLI for project context, memory\n  add\u002Fsearch\u002Flist\u002Fdelete, semantic profile operations, filters, formatting,\n  config API wrappers, and LangGraph tool helpers.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Python SDK And CLI\n\nUse this sub-skill when a task names `memmachine_client`, `MemMachineClient`,\n`Project`, `Memory`, `Config`, `mem-cli`, `memmachine`, Python memory add or\nsearch, semantic categories\u002Ftags\u002Ffeatures, metadata filters, `agent_mode`, or\nLangGraph memory tools.\n\n## Route Within This Sub-skill\n\n- Read [python-sdk-reference.md](references\u002Fpython-sdk-reference.md) for the\n  verified Python object model, method signatures, and return-shape notes.\n- Read [memory-workflows.md](references\u002Fmemory-workflows.md) for project\u002Fcontext\n  setup, add\u002Fsearch\u002Flist\u002Fdelete, semantic feature\u002Fcategory\u002Ftag workflows,\n  filters, and validation patterns.\n- Read [cli-reference.md](references\u002Fcli-reference.md) for `mem-cli` and\n  `memmachine` command shapes, environment variables, JSON flags, and safe\n  examples.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) when imports,\n  base URLs, project context, filters, closed clients, or server responses fail.\n- Run [mem_cli_smoke.py](scripts\u002Fmem_cli_smoke.py) to inspect CLI parser\u002Fhelp or\n  build safe command examples without contacting a server.\n- Run [python_client_recipe.py](scripts\u002Fpython_client_recipe.py) to print a\n  minimal Python SDK recipe or optionally run a live health\u002Fadd\u002Fsearch demo only\n  when explicit live arguments are supplied.\n\n## Quick Python Pattern\n\n```python\nfrom memmachine_client import MemMachineClient\n\nclient = MemMachineClient(base_url=\"http:\u002F\u002Flocalhost:8080\", api_key=None)\ntry:\n    project = client.get_or_create_project(org_id=\"my-org\", project_id=\"my-project\")\n    memory = project.memory(\n        metadata={\"user_id\": \"alice\", \"agent_id\": \"assistant\", \"session_id\": \"demo\"}\n    )\n    memory.add(\"Alice prefers aisle seats.\", metadata={\"category\": \"travel\"})\n    results = memory.search(\"What seating does Alice prefer?\", limit=5)\nfinally:\n    client.close()\n```\n\nUse explicit `org_id`, `project_id`, and memory metadata instead of relying on\nambient defaults. Keep API keys in environment variables or secret stores.\n\n## Quick CLI Pattern\n\n```bash\nmem-cli --base-url \"http:\u002F\u002Flocalhost:8080\" memory add \\\n  \"Alice prefers aisle seats.\" \\\n  --org-id \"my-org\" --project-id \"my-project\" \\\n  --metadata user_id=alice --metadata agent_id=assistant \\\n  --metadata category=travel\n\nmem-cli --base-url \"http:\u002F\u002Flocalhost:8080\" memory search \\\n  \"What seating does Alice prefer?\" \\\n  --org-id \"my-org\" --project-id \"my-project\" --limit 5\n```\n\nGlobal flags such as `--base-url` and `--api-key` come before the subcommand.\nProject context flags belong on `projects` or `memory` subcommands.\n\n## Decision Points\n\n- **SDK or CLI?** Use SDK for application code and tests; use CLI for ad-hoc\n  inspection, shell workflows, and agent memory retrieval\u002Faddition.\n- **Filter style?** Use modern `filter=\"metadata.category = 'travel'\"` for\n  boolean logic. Use `filter_dict` only for simple legacy equality filters.\n- **Semantic or episodic?** `MemoryType` supports `episodic` and `semantic`.\n  Adding to both may be useful, but verify the server configuration supports\n  both before assuming results appear in both surfaces.\n- **Agent mode?** `agent_mode=True` asks the server retrieval agent to do richer\n  query handling. It needs server-side LLM\u002Freranker resources; use ordinary\n  search first for simple lookups.\n- **LangGraph tools?** Use `MemMachineTools` or helper factories when an agent\n  runtime expects callable add\u002Fsearch tools. Ensure framework dependencies are\n  installed separately.\n\n## Non-goals And Cross-links\n\n- Server YAML, storage\u002Fprovider resources, Docker, MCP, and REST deployment\n  details belong in\n  [server-configuration-and-memory-engines](..\u002Fserver-configuration-and-memory-engines\u002FSKILL.md).\n- Framework adapters beyond the Python LangGraph helper surface belong in\n  [integrations-and-migration](..\u002Fintegrations-and-migration\u002FSKILL.md).\n- `@memmachine\u002Fclient` belongs in\n  [typescript-rest-client](..\u002Ftypescript-rest-client\u002FSKILL.md).\n- Endpoint\u002Fmodel translation details shared across SDKs are in the root\n  [REST API and data models reference](..\u002F..\u002Freferences\u002Frest-api-and-data-models.md).\n","# Python SDK And CLI\n\nUse this sub-skill when a task names `memmachine_client`, `MemMachineClient`,\n`Project`, `Memory`, `Config`, `mem-cli`, `memmachine`, Python memory add or\nsearch, semantic categories\u002Ftags\u002Ffeatures, metadata filters, `agent_mode`, or\nLangGraph memory tools.\n\n## Route Within This Sub-skill\n\n- Read [python-sdk-reference.md](references\u002Fpython-sdk-reference.md) for the\n  verified Python object model, method signatures, and return-shape notes.\n- Read [memory-workflows.md](references\u002Fmemory-workflows.md) for project\u002Fcontext\n  setup, add\u002Fsearch\u002Flist\u002Fdelete, semantic feature\u002Fcategory\u002Ftag workflows,\n  filters, and validation patterns.\n- Read [cli-reference.md](references\u002Fcli-reference.md) for `mem-cli` and\n  `memmachine` command shapes, environment variables, JSON flags, and safe\n  examples.\n- Read [troubleshooting.md](references\u002Ftroubleshooting.md) when imports,\n  base URLs, project context, filters, closed clients, or server responses fail.\n- Run [mem_cli_smoke.py](scripts\u002Fmem_cli_smoke.py) to inspect CLI parser\u002Fhelp or\n  build safe command examples without contacting a server.\n- Run [python_client_recipe.py](scripts\u002Fpython_client_recipe.py) to print a\n  minimal Python SDK recipe or optionally run a live health\u002Fadd\u002Fsearch demo only\n  when explicit live arguments are supplied.\n\n## Quick Python Pattern\n\n```python\nfrom memmachine_client import MemMachineClient\n\nclient = MemMachineClient(base_url=\"http:\u002F\u002Flocalhost:8080\", api_key=None)\ntry:\n    project = client.get_or_create_project(org_id=\"my-org\", project_id=\"my-project\")\n    memory = project.memory(\n        metadata={\"user_id\": \"alice\", \"agent_id\": \"assistant\", \"session_id\": \"demo\"}\n    )\n    memory.add(\"Alice prefers aisle seats.\", metadata={\"category\": \"travel\"})\n    results = memory.search(\"What seating does Alice prefer?\", limit=5)\nfinally:\n    client.close()\n```\n\nUse explicit `org_id`, `project_id`, and memory metadata instead of relying on\nambient defaults. Keep API keys in environment variables or secret stores.\n\n## Quick CLI Pattern\n\n```bash\nmem-cli --base-url \"http:\u002F\u002Flocalhost:8080\" memory add \\\n  \"Alice prefers aisle seats.\" \\\n  --org-id \"my-org\" --project-id \"my-project\" \\\n  --metadata user_id=alice --metadata agent_id=assistant \\\n  --metadata category=travel\n\nmem-cli --base-url \"http:\u002F\u002Flocalhost:8080\" memory search \\\n  \"What seating does Alice prefer?\" \\\n  --org-id \"my-org\" --project-id \"my-project\" --limit 5\n```\n\nGlobal flags such as `--base-url` and `--api-key` come before the subcommand.\nProject context flags belong on `projects` or `memory` subcommands.\n\n## Decision Points\n\n- **SDK or CLI?** Use SDK for application code and tests; use CLI for ad-hoc\n  inspection, shell workflows, and agent memory retrieval\u002Faddition.\n- **Filter style?** Use modern `filter=\"metadata.category = 'travel'\"` for\n  boolean logic. Use `filter_dict` only for simple legacy equality filters.\n- **Semantic or episodic?** `MemoryType` supports `episodic` and `semantic`.\n  Adding to both may be useful, but verify the server configuration supports\n  both before assuming results appear in both surfaces.\n- **Agent mode?** `agent_mode=True` asks the server retrieval agent to do richer\n  query handling. It needs server-side LLM\u002Freranker resources; use ordinary\n  search first for simple lookups.\n- **LangGraph tools?** Use `MemMachineTools` or helper factories when an agent\n  runtime expects callable add\u002Fsearch tools. Ensure framework dependencies are\n  installed separately.\n\n## Non-goals And Cross-links\n\n- Server YAML, storage\u002Fprovider resources, Docker, MCP, and REST deployment\n  details belong in\n  [server-configuration-and-memory-engines](..\u002Fserver-configuration-and-memory-engines\u002FSKILL.md).\n- Framework adapters beyond the Python LangGraph helper surface belong in\n  [integrations-and-migration](..\u002Fintegrations-and-migration\u002FSKILL.md).\n- `@memmachine\u002Fclient` belongs in\n  [typescript-rest-client](..\u002Ftypescript-rest-client\u002FSKILL.md).\n- Endpoint\u002Fmodel translation details shared across SDKs are in the root\n  [REST API and data models reference](..\u002F..\u002Freferences\u002Frest-api-and-data-models.md).\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill python-sdk-and-cli",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill python-sdk-and-cli",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill python-sdk-and-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-reference.md","REFERENCE","参考文档",4079,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Freferences\u002Fcli-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmemory-workflows.md",5313,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Freferences\u002Fmemory-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fpython-sdk-reference.md",6853,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Freferences\u002Fpython-sdk-reference.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",3711,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fmem_cli_smoke.py","SCRIPT","脚本",2406,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Fscripts\u002Fmem_cli_smoke.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fpython_client_recipe.py",2956,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmem-machine\u002Fsub-skills\u002Fpython-sdk-and-cli\u002Fscripts\u002Fpython_client_recipe.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]