{"components":[{"slug":"grok-xai","name":"Grok (xAI)","summary":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","kind":"runtime","homepage":"https://x.ai","docsUrl":"https://docs.x.ai","publisher":"xAI","license":"proprietary","hasMcp":true,"hasApi":true,"costRange":"seat","costNotes":"API usage and SuperGrok / Heavy subscription are different meters. CLI --single is the local agent compute slice.","composabilityRationale":"CLI --single, JSON schema, MCP/skills. Subscription quota is the operational bound, not an API glue problem.","functions":["generate","reason","search","code","tool-call","connect"],"slices":[{"functionId":"reason","label":"Grok Heavy CLI","note":"Local grok-heavy --single for structured jobs","cost":"Heavy subscription quota"},{"functionId":"generate","label":"xAI API","note":"Hosted completions","cost":"usage"},{"functionId":"search","label":"Search","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"code","label":"Code","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"connect","label":"Connect","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"}],"tweets":[{"url":"https://x.com/cryptopunk7213/status/2087242425681256472","author":"x.com","text":"Introducing Grok Bot, now in early beta. Bots are AI teammates that do real work for you. They sign in to your tools, use them just like you do, and come back ..."},{"url":"https://x.com/KanikaBK/article/2076954281413165090","author":"x.com","text":"Grok 4.5 is described by xAI as its flagship model for code and general work, with agentic tool calling, configurable reasoning, and support for long-context ..."},{"url":"https://x.com/mvanhorn/article/2077548703410540669","author":"x.com","text":"Some of Grok Build's most foundational tools are not xAI's at all. The third-party notices are explicit: `apply_patch`, `grep_files`, `list_dir`, and `read_file ..."}],"sources":[{"kind":"docs","label":"xAI docs","url":"https://docs.x.ai","at":"2026-09-12T00:00:00Z"},{"kind":"web","label":"x.ai","url":"https://x.ai","at":"2026-09-12T00:00:00Z"}],"origin":"seed","sector":"dev-harness","notes":[{"authorKind":"human","body":"Leyline intake uses grok-heavy --single the way Soundcheck's planner does.","at":"2026-09-12T00:00:00Z"}],"score":21,"explain":{"score":21,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"value":0.3,"contribution":0.054,"why":"A licence is declared. Documentation is available.","sources":[],"evidence":"observed"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"value":0.0867528411160754,"contribution":0.012145397756250557,"why":"1 stored human notes (component-record).","sources":[],"evidence":"observed"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[{"kind":"docs","label":"xAI docs","url":"https://docs.x.ai","at":"2026-09-12T00:00:00Z"}],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":1,"contribution":0.1,"why":"An MCP surface is declared. An API is declared. Cost is seat. 3 of 3 checklist fields are complete.","sources":[{"kind":"docs","label":"xAI docs","url":"https://docs.x.ai","at":"2026-09-12T00:00:00Z"}],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.3284952023094184,"contribution":0.04598932832331858,"why":"2 sources cover 2 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.","sources":[{"kind":"docs","label":"xAI docs","url":"https://docs.x.ai","at":"2026-09-12T00:00:00Z"},{"kind":"web","label":"x.ai","url":"https://x.ai","at":"2026-09-12T00:00:00Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["Agent use: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"createdAt":"2026-09-11T16:33:46.085Z","updatedAt":"2026-09-13T08:56:02.849Z","recordId":"cmp_grok-xai","claims":{"name":"Grok (xAI)","summary":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","kind":"runtime","publisher":"xAI","homepage":"https://x.ai","docsUrl":"https://docs.x.ai","license":"proprietary","costRange":"seat","costNotes":"API usage and SuperGrok / Heavy subscription are different meters. CLI --single is the local agent compute slice.","functions":["generate","reason","search","code","tool-call","connect"],"slices":[{"functionId":"reason","label":"Grok Heavy CLI","note":"Local grok-heavy --single for structured jobs","cost":"Heavy subscription quota"},{"functionId":"generate","label":"xAI API","note":"Hosted completions","cost":"usage"},{"functionId":"search","label":"Search","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"code","label":"Code","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"},{"functionId":"connect","label":"Connect","note":"Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.","cost":"seat"}],"interfaces":[{"kind":"mcp"},{"kind":"http"}],"composabilityRationale":"CLI --single, JSON schema, MCP/skills. Subscription quota is the operational bound, not an API glue problem."},"interfaces":[{"kind":"mcp"},{"kind":"http"}],"relations":[{"from":"grok-xai","to":"openai-codex","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"grok-xai","to":"claude-code","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"grok-xai","to":"cursor","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"grok-xai","to":"kogiqa-mcp-web-browser","kind":"fills-same-slot-as","note":"Shared functions code, connect, generate, search. Can fill the same function slot."},{"from":"grok-xai","to":"monid","kind":"fills-same-slot-as","note":"Shared functions connect, search, tool-call. Can fill the same function slot."},{"from":"grok-xai","to":"41-open-source-llms-evaluated-on-19-benchmarks","kind":"fills-same-slot-as","note":"Shared functions generate, reason, search. Can fill the same function slot."},{"from":"grok-xai","to":"exa","kind":"fills-same-slot-as","note":"Shared functions connect, search, tool-call. Can fill the same function slot."},{"from":"grok-xai","to":"executor","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."}],"signals":[{"key":"has_license","value":1,"source":"component-record","method":"declared-license","observedAt":"2026-09-13T08:56:02.849Z"},{"key":"has_docs","value":1,"source":"component-record","method":"declared-docs","observedAt":"2026-09-13T08:56:02.849Z"},{"key":"human_note_count","value":1,"source":"component-record","method":"stored-notes","observedAt":"2026-09-13T08:56:02.849Z"}],"functionProbabilities":[],"claimVerification":[]},{"slug":"claude-code","name":"Claude Code","summary":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","kind":"runtime","homepage":"https://code.claude.com","publisher":"Anthropic","license":"proprietary","hasMcp":true,"hasApi":true,"costRange":"seat","composabilityRationale":"Native MCP, skills, and CLAUDE.md. Easy to add a Leyline scour skill. API is a different slice from the CLI harness.","functions":["code","reason","tool-call","connect","compose"],"slices":[{"functionId":"code","label":"CLI agent","note":"Repo-native coding loop","cost":"Claude seat"},{"functionId":"connect","label":"MCP + skills","note":"Install Leyline scour","cost":"included"},{"functionId":"reason","label":"Reason","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"},{"functionId":"compose","label":"Compose","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"}],"tweets":[{"url":"https://x.com/godofprompt/status/2091489401109156328","author":"x.com","text":"Setting up a Claude Code agent means writing the config, the prompt, and tooling yourself every time. Most people give up before the first one works."},{"url":"https://x.com/PrajwalTomar_/status/2084980287717675226","author":"x.com","text":"Claude Code Subagents Are CRACKED Now. Here's My Exact Workflow. Most people just unleashed a swarm of subagents, watched it burn through context and money, and ..."},{"url":"https://x.com/kr0der/status/2092628896063848896","author":"x.com","text":"WTF a Claude Code agent just proactively messaged another one of my Claude agents, i'm mind blown one Claude agent was building a mobile app and was ..."}],"sources":[{"kind":"web","label":"Claude Code","url":"https://code.claude.com","at":"2026-09-12T00:00:00Z"}],"origin":"seed","sector":"dev-harness","notes":[],"score":15,"explain":{"score":15,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"value":0.15,"contribution":0.027,"why":"A licence is declared.","sources":[],"evidence":"observed"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":1,"contribution":0.1,"why":"An MCP surface is declared. An API is declared. Cost is seat. 3 of 3 checklist fields are complete.","sources":[],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.18107144632819594,"contribution":0.025350002485947435,"why":"1 sources cover 1 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.","sources":[{"kind":"web","label":"Claude Code","url":"https://code.claude.com","at":"2026-09-12T00:00:00Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["Agent use: insufficient evidence","Human notes: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"createdAt":"2026-09-11T16:33:49.485Z","updatedAt":"2026-09-13T08:56:02.851Z","recordId":"cmp_claude-code","claims":{"name":"Claude Code","summary":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","kind":"runtime","publisher":"Anthropic","homepage":"https://code.claude.com","license":"proprietary","costRange":"seat","functions":["code","reason","tool-call","connect","compose"],"slices":[{"functionId":"code","label":"CLI agent","note":"Repo-native coding loop","cost":"Claude seat"},{"functionId":"connect","label":"MCP + skills","note":"Install Leyline scour","cost":"included"},{"functionId":"reason","label":"Reason","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"},{"functionId":"compose","label":"Compose","note":"Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.","cost":"seat"}],"interfaces":[{"kind":"mcp"},{"kind":"http"}],"composabilityRationale":"Native MCP, skills, and CLAUDE.md. Easy to add a Leyline scour skill. API is a different slice from the CLI harness."},"interfaces":[{"kind":"mcp"},{"kind":"http"}],"relations":[{"from":"claude-code","to":"openai-codex","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"claude-code","to":"cursor","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"claude-code","to":"grok-xai","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"claude-code","to":"executor","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."},{"from":"claude-code","to":"shadcn-ui","kind":"fills-same-slot-as","note":"Shared functions code, compose. Can fill the same function slot."},{"from":"claude-code","to":"mobbin-mcp","kind":"fills-same-slot-as","note":"Shared functions compose, connect. Can fill the same function slot."},{"from":"claude-code","to":"openship","kind":"fills-same-slot-as","note":"Shared functions connect, tool-call. Can fill the same function slot."},{"from":"claude-code","to":"monetization-gateway","kind":"fills-same-slot-as","note":"Shared functions connect, tool-call. Can fill the same function slot."}],"signals":[{"key":"has_license","value":1,"source":"component-record","method":"declared-license","observedAt":"2026-09-13T08:56:02.851Z"}],"functionProbabilities":[],"claimVerification":[]},{"slug":"openai-codex","name":"Codex","summary":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","kind":"runtime","homepage":"https://openai.com/codex","publisher":"OpenAI","license":"proprietary","hasMcp":true,"hasApi":true,"costRange":"seat","composabilityRationale":"CLI and IDE hooks. MCP support varies by surface. Treat Codex as a harness slice, not an inference gateway.","functions":["code","reason","tool-call","connect"],"slices":[{"functionId":"code","label":"Codex CLI","note":"Local coding agent","cost":"ChatGPT / API seat"},{"functionId":"reason","label":"Reason","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"},{"functionId":"connect","label":"Connect","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"}],"tweets":[{"url":"https://x.com/OpenAIDevs/status/2098130570048045453","author":"x.com","text":"Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management."},{"url":"https://x.com/emollick/status/2098059793986470291","author":"x.com","text":"A critical factor in using agents successfully in Codex and Code is deciding when & how to use these options. If you are not steering long-running agentic ..."},{"url":"https://x.com/OpenAIDevs/status/2090230646497251387","author":"x.com","text":"Teams are using the open-source Codex harness to bring agents into the tools they already use, from internal apps to operations dashboards."}],"sources":[{"kind":"web","label":"OpenAI Codex","url":"https://openai.com/codex","at":"2026-09-12T00:00:00Z"}],"origin":"seed","sector":"dev-harness","notes":[],"score":15,"explain":{"score":15,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"value":0.15,"contribution":0.027,"why":"A licence is declared.","sources":[],"evidence":"observed"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":1,"contribution":0.1,"why":"An MCP surface is declared. An API is declared. Cost is seat. 3 of 3 checklist fields are complete.","sources":[],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.18107144632819594,"contribution":0.025350002485947435,"why":"1 sources cover 1 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.","sources":[{"kind":"web","label":"OpenAI Codex","url":"https://openai.com/codex","at":"2026-09-12T00:00:00Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["Agent use: insufficient evidence","Human notes: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"createdAt":"2026-09-11T16:33:50.760Z","updatedAt":"2026-09-13T08:56:02.854Z","recordId":"cmp_openai-codex","claims":{"name":"Codex","summary":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","kind":"runtime","publisher":"OpenAI","homepage":"https://openai.com/codex","license":"proprietary","costRange":"seat","functions":["code","reason","tool-call","connect"],"slices":[{"functionId":"code","label":"Codex CLI","note":"Local coding agent","cost":"ChatGPT / API seat"},{"functionId":"reason","label":"Reason","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"},{"functionId":"connect","label":"Connect","note":"OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.","cost":"seat"}],"interfaces":[{"kind":"mcp"},{"kind":"http"}],"composabilityRationale":"CLI and IDE hooks. MCP support varies by surface. Treat Codex as a harness slice, not an inference gateway."},"interfaces":[{"kind":"mcp"},{"kind":"http"}],"relations":[{"from":"openai-codex","to":"claude-code","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"openai-codex","to":"cursor","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"openai-codex","to":"grok-xai","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"openai-codex","to":"executor","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."},{"from":"openai-codex","to":"openship","kind":"fills-same-slot-as","note":"Shared functions connect, tool-call. Can fill the same function slot."},{"from":"openai-codex","to":"monetization-gateway","kind":"fills-same-slot-as","note":"Shared functions connect, tool-call. Can fill the same function slot."},{"from":"openai-codex","to":"rea","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."},{"from":"openai-codex","to":"agentmemory","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."}],"signals":[{"key":"has_license","value":1,"source":"component-record","method":"declared-license","observedAt":"2026-09-13T08:56:02.854Z"}],"functionProbabilities":[],"claimVerification":[]},{"slug":"cursor","name":"Cursor","summary":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","kind":"runtime","homepage":"https://cursor.com","publisher":"Anysphere","license":"proprietary","hasMcp":true,"hasApi":false,"costRange":"seat","composabilityRationale":"MCP and rules files make catalogue skills installable. Closed editor means the slice is 'harness', not 'library'.","functions":["code","reason","tool-call","connect","retrieve"],"slices":[{"functionId":"code","label":"Inline agent","note":"Edit in the repo","cost":"seat"},{"functionId":"connect","label":"MCP hosts","note":"Attach Leyline or other servers","cost":"included on seat"},{"functionId":"reason","label":"Reason","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"},{"functionId":"retrieve","label":"Retrieve","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"}],"tweets":[{"url":"https://x.com/cursor_ai/status/2085464617694777762","author":"x.com","text":"Cursor now supports Agent Plugins, an open standard for bundling skills and MCP servers for use across agents."},{"url":"https://x.com/cursor_ai/status/2084317547608911986","author":"x.com","text":"Cursor Cloud agents are now 20-30% more token efficient, and 80% more efficient on runs with computer use. We've improved how they handle MCPs, skills, and ..."},{"url":"https://x.com/devagrawal09/article/2089089101010239926","author":"x.com","text":"Cursor's agent could migrate Solid to React because that direction asks for nothing. The direction that asks for something is the one that needs a codemod, not ..."}],"sources":[{"kind":"web","label":"Cursor","url":"https://cursor.com","at":"2026-09-12T00:00:00Z"}],"origin":"seed","sector":"dev-harness","notes":[],"score":12,"explain":{"score":12,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"value":0.15,"contribution":0.027,"why":"A licence is declared.","sources":[],"evidence":"observed"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":0.6666666666666666,"contribution":0.06666666666666667,"why":"An MCP surface is declared. No API is declared. Cost is seat. 2 of 3 checklist fields are complete.","sources":[],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.18107144632819594,"contribution":0.025350002485947435,"why":"1 sources cover 1 evidence types. The latest dated evidence is 2026-09-12. Freshness is omitted unless observed as a signal.","sources":[{"kind":"web","label":"Cursor","url":"https://cursor.com","at":"2026-09-12T00:00:00Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["Agent use: insufficient evidence","Human notes: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"createdAt":"2026-09-11T16:33:47.438Z","updatedAt":"2026-09-13T08:56:02.860Z","recordId":"cmp_cursor","claims":{"name":"Cursor","summary":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","kind":"runtime","publisher":"Anysphere","homepage":"https://cursor.com","license":"proprietary","costRange":"seat","functions":["code","reason","tool-call","connect","retrieve"],"slices":[{"functionId":"code","label":"Inline agent","note":"Edit in the repo","cost":"seat"},{"functionId":"connect","label":"MCP hosts","note":"Attach Leyline or other servers","cost":"included on seat"},{"functionId":"reason","label":"Reason","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"},{"functionId":"tool-call","label":"Tool-call","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"},{"functionId":"retrieve","label":"Retrieve","note":"Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.","cost":"seat"}],"interfaces":[{"kind":"mcp"}],"composabilityRationale":"MCP and rules files make catalogue skills installable. Closed editor means the slice is 'harness', not 'library'."},"interfaces":[{"kind":"mcp"}],"relations":[{"from":"cursor","to":"openai-codex","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"cursor","to":"claude-code","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"cursor","to":"grok-xai","kind":"alternative-to","note":"Shared functions code, connect, reason, tool-call. Same kind and overlapping capability."},{"from":"cursor","to":"build-software-better-together","kind":"fills-same-slot-as","note":"Shared functions code, connect, retrieve, tool-call. Can fill the same function slot."},{"from":"cursor","to":"cognee","kind":"fills-same-slot-as","note":"Shared functions code, connect, retrieve. Can fill the same function slot."},{"from":"cursor","to":"executor","kind":"fills-same-slot-as","note":"Shared functions code, connect. Can fill the same function slot."},{"from":"cursor","to":"zillow-data-apis","kind":"fills-same-slot-as","note":"Shared functions connect, retrieve. Can fill the same function slot."},{"from":"cursor","to":"exa","kind":"fills-same-slot-as","note":"Shared functions connect, retrieve, tool-call. Can fill the same function slot."}],"signals":[{"key":"has_license","value":1,"source":"component-record","method":"declared-license","observedAt":"2026-09-13T08:56:02.860Z"}],"functionProbabilities":[],"claimVerification":[]},{"slug":"pageindex","name":"PageIndex","summary":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","kind":"app","homepage":"https://pageindex.ai","repoUrl":"https://github.com/VectifyAI/PageIndex","docsUrl":"https://docs.pageindex.ai","publisher":"","license":"MIT","hasMcp":true,"hasApi":false,"costRange":"unknown","composabilityRationale":"","functions":["index","reason","embed","memory","retrieve"],"functionProbabilities":[{"functionId":"index","value":0.8,"source":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md","method":"lexical","observedAt":"2026-09-29T00:00:00.000Z"},{"functionId":"reason","value":0.8,"source":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md","method":"lexical","observedAt":"2026-09-29T00:00:00.000Z"},{"functionId":"embed","value":0.72,"source":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md","method":"lexical","observedAt":"2026-09-29T00:00:00.000Z"},{"functionId":"memory","value":0.72,"source":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md","method":"lexical","observedAt":"2026-09-29T00:00:00.000Z"},{"functionId":"retrieve","value":0.72,"source":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md","method":"lexical","observedAt":"2026-09-29T00:00:00.000Z"}],"slices":[{"functionId":"index","label":"Index","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"reason","label":"Reason","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"embed","label":"Embed","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"memory","label":"Memory","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"retrieve","label":"Retrieve","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"}],"tweets":[],"sources":[{"kind":"human","label":"Catalogue resource card","excerpt":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md\nPageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","at":"2026-09-29T00:00:00.000Z"},{"kind":"human","label":"Catalogue resource card","excerpt":"Cloud — PAGEINDEX_API_KEY; managed indexing/OCR/storage; chat still uses your model; MCP + folders/metadata (Cloud-only features).","at":"2026-09-29T00:00:00.000Z"}],"interfaces":[{"kind":"mcp"}],"origin":"seed","notes":[],"createdAt":"2026-09-29T00:00:00.000Z","updatedAt":"2026-09-29T00:00:00.000Z","stagingSeed":"leyline-0.3.0-staging","recordId":"cmp_pageindex","claims":{"name":"PageIndex","summary":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","kind":"app","publisher":"","homepage":"https://pageindex.ai","repoUrl":"https://github.com/VectifyAI/PageIndex","docsUrl":"https://docs.pageindex.ai","license":"MIT","costRange":"unknown","functions":["index","reason","embed","memory","retrieve"],"slices":[{"functionId":"index","label":"Index","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"reason","label":"Reason","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"embed","label":"Embed","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"memory","label":"Memory","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"},{"functionId":"retrieve","label":"Retrieve","note":"PageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","cost":"unknown"}],"interfaces":[{"kind":"mcp"}],"composabilityRationale":""},"relations":[{"from":"pageindex","to":"llamaindex","kind":"fills-same-slot-as","note":"Shared functions embed, index, memory, retrieve. Can fill the same function slot."},{"from":"pageindex","to":"cognee","kind":"fills-same-slot-as","note":"Shared functions embed, memory, retrieve. Can fill the same function slot."},{"from":"pageindex","to":"local-faiss-mcp-server","kind":"fills-same-slot-as","note":"Shared functions embed, index, memory, retrieve. Can fill the same function slot."},{"from":"pageindex","to":"alibaba-model-studio","kind":"fills-same-slot-as","note":"Shared functions embed, reason. Can fill the same function slot."},{"from":"pageindex","to":"octen","kind":"fills-same-slot-as","note":"Shared functions embed, retrieve. Can fill the same function slot."},{"from":"pageindex","to":"build-software-better-together","kind":"fills-same-slot-as","note":"Shared functions index, memory, retrieve. Can fill the same function slot."},{"from":"pageindex","to":"turbopuffer","kind":"fills-same-slot-as","note":"Shared functions embed, memory. Can fill the same function slot."},{"from":"pageindex","to":"local-office","kind":"fills-same-slot-as","note":"Shared functions memory, retrieve. Can fill the same function slot."}],"signals":[{"key":"has_license","value":1,"source":"component-record","method":"declared-license","observedAt":"2026-09-29T00:00:00.000Z"},{"key":"has_docs","value":1,"source":"component-record","method":"declared-docs","observedAt":"2026-09-29T00:00:00.000Z"}],"claimVerification":[],"explain":{"score":12,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"value":0.3,"contribution":0.054,"why":"A licence is declared. Documentation is available.","sources":[],"evidence":"observed"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"why":"insufficient evidence","sources":[{"kind":"human","label":"Catalogue resource card","excerpt":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md\nPageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","at":"2026-09-29T00:00:00.000Z"},{"kind":"human","label":"Catalogue resource card","excerpt":"Cloud — PAGEINDEX_API_KEY; managed indexing/OCR/storage; chat still uses your model; MCP + folders/metadata (Cloud-only features).","at":"2026-09-29T00:00:00.000Z"}],"evidence":"insufficient"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":0.3333333333333333,"contribution":0.03333333333333333,"why":"An MCP surface is declared. No API is declared. Cost is unknown. 1 of 3 checklist fields are complete.","sources":[],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.22849520230941842,"contribution":0.031989328323318585,"why":"2 sources cover 1 evidence types. The latest dated evidence is 2026-09-29. Freshness is omitted unless observed as a signal.","sources":[{"kind":"human","label":"Catalogue resource card","excerpt":"06 Knowledge Library/Resources/coding/2026-09-29-vectifyai-pageindex.md\nPageIndex (MIT, Python) is VectifyAI’s vectorless, reasoning-based RAG engine. First-party pitch: build a hierarchical tree index per document, then let an LLM reason through that tree (human-like section navigation) instead of embedding chunks into a vector database.","at":"2026-09-29T00:00:00.000Z"},{"kind":"human","label":"Catalogue resource card","excerpt":"Cloud — PAGEINDEX_API_KEY; managed indexing/OCR/storage; chat still uses your model; MCP + folders/metadata (Cloud-only features).","at":"2026-09-29T00:00:00.000Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["Agent use: insufficient evidence","Human notes: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"score":12}]}