{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-adongwanai--agentguide","slug":"adongwanai--agentguide","name":"AgentGuide","type":"repo","url":"https://github.com/adongwanai/AgentGuide","page_url":"https://unfragile.ai/adongwanai--agentguide","categories":["ai-agents","rag-knowledge"],"tags":["agenticrag","ai-agent","crewai","graphrag","grpo","interview","job-hunting","langchain","llm","multi-agent","rag","sft","tutorial"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-adongwanai--agentguide__cap_0","uri":"capability://planning.reasoning.structured.learning.path.generation.for.ai.agent.roles","name":"structured learning path generation for ai agent roles","description":"Generates role-specific learning roadmaps (Algorithm Engineer vs Development Engineer) by organizing 300+ curated resources into sequential, interview-annotated learning paths. Uses numeric prefix-based directory ordering (01-theory → 02-tech-stack → 03-practice → 04-interview) to enforce pedagogical progression, with each topic tagged for job-testing relevance and role applicability. Implements resource aggregation pattern that cites external materials rather than reproducing them, enabling lightweight maintenance while preserving signal quality.","intents":["I need a structured path to transition from software engineering to AI agent development roles","I want to understand which topics are actually tested in interviews for agent engineer positions","I need to know whether to focus on research (algorithm engineer) or systems building (development engineer) track"],"best_for":["Career changers transitioning into AI agent roles","Job seekers preparing for agent engineer interviews","Teams onboarding new engineers into agent development"],"limitations":["Content is primarily in Chinese/English mixed; non-native speakers may face comprehension barriers","Roadmaps are static documents, not adaptive — don't adjust based on learner progress or skill gaps","No built-in progress tracking or personalization — learners must manually navigate and track completion"],"requires":["Web browser to access GitHub Pages deployment","Basic understanding of LLM fundamentals (transformers, attention)","Ability to read and follow external resource links (no offline mode)"],"input_types":["none — read-only learning resource"],"output_types":["structured learning paths (HTML/Markdown)","interview question banks","project catalogs"],"categories":["planning-reasoning","education-career-development"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_1","uri":"capability://planning.reasoning.curated.agent.framework.comparison.and.evaluation","name":"curated agent framework comparison and evaluation","description":"Maintains a structured comparison matrix of agent frameworks (LangGraph, CrewAI, AutoGen, etc.) with evaluation criteria covering architecture patterns, memory systems, tool-calling approaches, and production readiness. Implements a reference-aggregation pattern that indexes official documentation and research papers rather than reimplementing framework knowledge, enabling rapid updates as frameworks evolve. Includes 12-factor agent architecture principles and agent evaluation guidelines that provide decision frameworks for framework selection.","intents":["I need to choose between LangGraph, CrewAI, and AutoGen for my multi-agent system","I want to understand the architectural tradeoffs between different agent frameworks","I need evaluation criteria to assess whether a framework is production-ready"],"best_for":["Engineering teams selecting agent frameworks for new projects","Architects designing multi-agent systems","Developers migrating between agent frameworks"],"limitations":["Comparison is static documentation, not a live evaluation tool — doesn't run benchmarks or performance tests","Framework landscape evolves faster than documentation can be updated; some comparisons may lag 2-3 months behind latest releases","No hands-on sandbox environment for testing frameworks side-by-side"],"requires":["Understanding of agent architecture concepts (ReAct, CoT, tool-calling)","Familiarity with at least one LLM framework (LangChain, LlamaIndex, etc.)","Access to GitHub Pages deployment"],"input_types":["none — reference documentation"],"output_types":["comparison matrices (HTML/Markdown)","architecture diagrams","evaluation checklists"],"categories":["planning-reasoning","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_10","uri":"capability://data.processing.analysis.markdown.to.json.resource.indexing.pipeline","name":"markdown-to-json resource indexing pipeline","description":"Automates conversion of Markdown documentation into a JSON index consumed by the frontend SPA. Implemented as Python scripts in scripts/ directory that parse Markdown frontmatter, extract topic hierarchies, and generate a searchable index. Enables rapid content updates without manual index maintenance, supporting the resource-aggregation pattern by keeping documentation and index in sync.","intents":["I need to add new learning content without manually updating the search index","I want to maintain a single source of truth (Markdown) that drives both documentation and navigation","I need to automate the documentation build pipeline"],"best_for":["Content maintainers managing large documentation collections","Teams implementing similar learning platforms","Projects using Markdown as the source of truth"],"limitations":["Pipeline is tightly coupled to AgentGuide's directory structure; not easily reusable for other projects","No incremental indexing; full rebuild required for any content change","Frontmatter parsing is custom; no standard schema (YAML, TOML) validation"],"requires":["Python 3.9+","Markdown files with consistent structure and frontmatter","GitHub Actions or local Python environment for running scripts"],"input_types":["Markdown files with frontmatter"],"output_types":["JSON index files","searchable metadata"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_11","uri":"capability://automation.workflow.github.pages.ci.cd.deployment.with.automated.resource.generation","name":"github pages ci/cd deployment with automated resource generation","description":"Implements a GitHub Actions workflow (.github/workflows/deploy-pages.yml) that automatically triggers resource indexing, builds the SPA, and deploys to GitHub Pages on every commit. Enables continuous deployment of documentation updates without manual build steps. Implements a fully automated pipeline from Markdown source to live website.","intents":["I want documentation changes to be live immediately after commit","I need to automate the build and deployment process","I want to avoid manual deployment steps and human error"],"best_for":["Open-source projects using GitHub Pages for documentation","Teams wanting zero-friction documentation updates","Projects with frequent content changes"],"limitations":["GitHub Pages has a 10-minute build timeout; large content sets may fail","No staging environment; all commits go directly to production","GitHub Actions minutes are limited for free tier; high-frequency commits may exceed quota"],"requires":["GitHub repository with Pages enabled","GitHub Actions workflow file (.github/workflows/deploy-pages.yml)","Python 3.9+ for resource indexing scripts"],"input_types":["Markdown files in docs/ directory"],"output_types":["Deployed website on GitHub Pages","JSON resource index"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_2","uri":"capability://memory.knowledge.rag.system.design.and.vector.database.reference","name":"rag system design and vector database reference","description":"Indexes RAG architecture patterns, vector database options (Pinecone, Weaviate, Milvus, Chroma), and document parsing strategies through curated reference documentation and research papers. Implements a knowledge-aggregation pattern that maps RAG papers to practical implementation guides, connecting theoretical foundations (agentic RAG, GraphRAG) to production tooling. Includes document parsing best practices covering PDF extraction, chunking strategies, and metadata preservation.","intents":["I need to understand the difference between traditional RAG and agentic RAG for my agent system","I want to choose the right vector database for my retrieval pipeline","I need to implement robust document parsing for heterogeneous document types"],"best_for":["Teams building retrieval-augmented generation systems","Engineers implementing knowledge bases for agents","Data engineers designing document ingestion pipelines"],"limitations":["Documentation is reference-only; no executable code examples or sample implementations provided","Vector database comparisons don't include performance benchmarks or cost analysis","Document parsing guide is theoretical; doesn't cover edge cases or failure modes in production"],"requires":["Understanding of embedding models and semantic search","Familiarity with vector database concepts (indexing, similarity search)","Knowledge of document formats (PDF, DOCX, HTML, etc.)"],"input_types":["none — reference documentation"],"output_types":["RAG architecture guides (Markdown)","vector database comparison tables","document parsing best practices"],"categories":["memory-knowledge","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_3","uri":"capability://text.generation.language.context.engineering.and.prompt.optimization.reference","name":"context engineering and prompt optimization reference","description":"Provides structured guidance on context window management, prompt engineering patterns, and token optimization strategies for agent systems. Covers context engineering principles (how to structure prompts for agents), memory system design (conversation history, episodic memory, semantic memory), and token budget allocation across multi-turn interactions. Implements a pattern-documentation approach that catalogs proven prompt structures and context management techniques from research and production systems.","intents":["I need to optimize my agent's context window usage to fit more conversation history","I want to understand how to structure prompts for multi-step reasoning tasks","I need to design a memory system that balances context length with retrieval quality"],"best_for":["LLM engineers optimizing prompt and context strategies","Agent developers designing memory systems","Teams working with context-limited models (mobile, edge deployment)"],"limitations":["Guidance is model-agnostic; doesn't provide model-specific optimization (e.g., Claude vs GPT-4 context handling)","No automated tools for measuring context efficiency or token usage","Patterns are documented but not validated against production metrics"],"requires":["Understanding of tokenization and token counting","Familiarity with LLM APIs and context window limits","Knowledge of prompt engineering basics"],"input_types":["none — reference documentation"],"output_types":["context engineering guides (Markdown)","prompt templates","memory system design patterns"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_4","uri":"capability://code.generation.editing.supervised.fine.tuning.sft.and.model.adaptation.guide","name":"supervised fine-tuning (sft) and model adaptation guide","description":"Documents SFT strategies for adapting foundation models to agent tasks, including data synthesis approaches, training pipeline design, and evaluation metrics specific to agent behavior. Covers how to generate synthetic training data for agent-specific tasks (tool-calling, reasoning, planning) and how to measure fine-tuning effectiveness. Implements a reference-aggregation pattern linking SFT research papers to practical implementation considerations.","intents":["I need to fine-tune a model to improve its tool-calling or reasoning capabilities","I want to generate synthetic training data for agent-specific tasks","I need to evaluate whether fine-tuning improved my agent's performance"],"best_for":["ML engineers customizing models for agent tasks","Teams with domain-specific agent requirements","Researchers exploring agent model adaptation"],"limitations":["Guide is theoretical; doesn't provide turnkey training code or data generation scripts","No cost analysis or compute requirement estimates for SFT pipelines","Evaluation metrics are conceptual; no automated evaluation harness provided"],"requires":["Experience with model training (PyTorch, Hugging Face, etc.)","Understanding of agent task requirements and evaluation","Access to compute resources for fine-tuning"],"input_types":["none — reference documentation"],"output_types":["SFT strategy guides (Markdown)","data synthesis patterns","evaluation frameworks"],"categories":["code-generation-editing","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_5","uri":"capability://planning.reasoning.agent.architecture.principles.and.design.patterns","name":"agent architecture principles and design patterns","description":"Codifies 12-factor agent architecture principles and design patterns for building production-grade agent systems. Covers agent lifecycle management, error handling, observability, sandboxing, and safety considerations. Implements a pattern-documentation approach that catalogs proven architectural decisions from production systems and research, enabling teams to avoid common pitfalls.","intents":["I need to design an agent system that's safe, observable, and maintainable in production","I want to understand the architectural tradeoffs between different agent design patterns","I need to implement proper error handling and recovery in my multi-agent system"],"best_for":["Architects designing production agent systems","Teams building safety-critical agent applications","Engineers migrating agents from prototype to production"],"limitations":["Principles are documented but not enforced by tooling; teams must implement manually","No reference implementation or starter template provided","Safety and sandboxing guidance is conceptual; doesn't include code examples"],"requires":["Understanding of agent architecture and lifecycle","Familiarity with production system design (monitoring, logging, error handling)","Knowledge of safety and security considerations for AI systems"],"input_types":["none — reference documentation"],"output_types":["architecture principles (Markdown)","design pattern catalogs","safety guidelines"],"categories":["planning-reasoning","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_6","uri":"capability://planning.reasoning.interview.preparation.and.job.hunting.resource.aggregation","name":"interview preparation and job-hunting resource aggregation","description":"Aggregates 300+ interview questions organized by role type (Algorithm Engineer, Development Engineer) and topic area, with explicit annotations for how each topic is tested in interviews. Covers LLM fundamentals, coding questions, algorithm problems, and HR/career negotiation topics. Implements a curated-signal pattern that includes only questions with direct interview relevance, avoiding generic LeetCode-style problems in favor of agent-specific technical depth.","intents":["I need to prepare for interviews for AI agent engineer roles","I want to understand what algorithm and system design questions are asked for agent positions","I need guidance on negotiating salary and career transition for AI roles"],"best_for":["Job seekers preparing for agent engineer interviews","Career changers transitioning into AI roles","Hiring managers preparing interview questions for agent positions"],"limitations":["Question bank is static; doesn't update with new interview trends or company-specific questions","No interactive practice environment or solution verification","Answers are referenced (links to external resources) rather than provided directly"],"requires":["Ability to read and follow external resource links","Understanding of LLM fundamentals and agent concepts","Time to work through 300+ questions"],"input_types":["none — reference documentation"],"output_types":["interview question banks (Markdown)","topic-specific question collections","HR/career guidance"],"categories":["planning-reasoning","education-career-development"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_7","uri":"capability://memory.knowledge.research.paper.indexing.and.agentic.rag.paper.collection","name":"research paper indexing and agentic rag paper collection","description":"Maintains a curated index of research papers relevant to agent development, with separate collections for agent papers and agentic RAG papers. Implements a resource-aggregation pattern that links to papers with brief context on their relevance to practical agent development. Enables researchers and engineers to quickly find foundational work (ReAct, CoT, tool-calling) and cutting-edge advances (agentic RAG, GraphRAG).","intents":["I need to understand the foundational research behind agent architectures (ReAct, CoT)","I want to learn about cutting-edge agentic RAG and GraphRAG approaches","I need to find papers on specific agent topics (memory, planning, tool-calling)"],"best_for":["Researchers exploring agent development","Engineers implementing cutting-edge agent patterns","Teams evaluating new agent research for production applicability"],"limitations":["Paper index is manually curated; may lag behind latest publications by weeks or months","No full-text search or semantic paper retrieval — must browse collections manually","No summaries or implementation guides for papers; links only"],"requires":["Access to paper repositories (arXiv, ACL, etc.)","Understanding of research paper abstracts and relevance","Time to read and synthesize multiple papers"],"input_types":["none — reference documentation"],"output_types":["paper collections (Markdown)","paper links with context","topic-specific paper groupings"],"categories":["memory-knowledge","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_8","uri":"capability://code.generation.editing.end.to.end.project.catalogs.and.workflow.examples","name":"end-to-end project catalogs and workflow examples","description":"Indexes open-source agent projects and official framework guides organized by complexity and use case. Implements a resource-aggregation pattern that catalogs existing projects rather than reimplementing them, enabling learners to study production code and adapt patterns. Covers agent workflows (multi-step reasoning, tool-calling chains, multi-agent coordination) with links to reference implementations.","intents":["I want to see a complete working example of a multi-agent system","I need to understand how to implement specific agent workflows (tool-calling, planning, memory)","I want to study production code patterns from open-source agent projects"],"best_for":["Developers learning by example","Teams building similar agent systems","Engineers implementing specific agent patterns"],"limitations":["Projects are external links; no guarantee of maintenance or continued support","No hands-on sandbox environment for running projects","Project quality and documentation vary; some may be outdated or incomplete"],"requires":["Ability to clone and run GitHub projects","Understanding of Python/Node.js and relevant frameworks","Environment setup (API keys, dependencies, etc.)"],"input_types":["none — reference documentation"],"output_types":["project catalogs (Markdown)","workflow examples (links to code)","implementation patterns"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-adongwanai--agentguide__cap_9","uri":"capability://automation.workflow.static.spa.frontend.with.resource.index.navigation","name":"static spa frontend with resource index navigation","description":"Provides a single-page application (SPA) frontend built with HTML/JavaScript that navigates a JSON-indexed resource collection. Implements a resource-index pipeline that converts Markdown documentation into a JSON index consumed by the frontend, enabling fast client-side search and navigation without server-side computation. Uses GitHub Pages for deployment, making the entire guide accessible without infrastructure costs.","intents":["I need to quickly navigate and search the learning guide","I want to browse resources by topic without slow page loads","I need offline-capable access to the learning guide"],"best_for":["Users accessing the guide from low-bandwidth environments","Teams deploying similar learning resources with minimal infrastructure","Learners preferring client-side search over server-side queries"],"limitations":["No server-side search or advanced query capabilities","SPA must load entire JSON index into memory; scales poorly beyond ~10MB of content","No user authentication or personalization","Offline mode requires manual caching; no service worker implementation"],"requires":["Modern web browser with JavaScript enabled","Network access to GitHub Pages deployment","JSON index generation pipeline (Python scripts in scripts/ directory)"],"input_types":["Markdown documentation files"],"output_types":["HTML SPA","JSON resource index","searchable navigation interface"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":49,"verified":false,"data_access_risk":"high","permissions":["Web browser to access GitHub Pages deployment","Basic understanding of LLM fundamentals (transformers, attention)","Ability to read and follow external resource links (no offline mode)","Understanding of agent architecture concepts (ReAct, CoT, tool-calling)","Familiarity with at least one LLM framework (LangChain, LlamaIndex, etc.)","Access to GitHub Pages deployment","Python 3.9+","Markdown files with consistent structure and frontmatter","GitHub Actions or local Python environment for running scripts","GitHub repository with Pages enabled"],"failure_modes":["Content is primarily in Chinese/English mixed; non-native speakers may face comprehension barriers","Roadmaps are static documents, not adaptive — don't adjust based on learner progress or skill gaps","No built-in progress tracking or personalization — learners must manually navigate and track completion","Comparison is static documentation, not a live evaluation tool — doesn't run benchmarks or performance tests","Framework landscape evolves faster than documentation can be updated; some comparisons may lag 2-3 months behind latest releases","No hands-on sandbox environment for testing frameworks side-by-side","Pipeline is tightly coupled to AgentGuide's directory structure; not easily reusable for other projects","No incremental indexing; full rebuild required for any content change","Frontmatter parsing is custom; no standard schema (YAML, TOML) validation","GitHub Pages has a 10-minute build timeout; large content sets may fail","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.568457570377118,"quality":0.49,"ecosystem":0.7000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.3,"quality":0.2,"ecosystem":0.15,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.549Z","last_scraped_at":"2026-04-22T08:01:53.258Z","last_commit":"2026-04-20T09:22:42Z"},"community":{"stars":4105,"forks":405,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=adongwanai--agentguide","compare_url":"https://unfragile.ai/compare?artifact=adongwanai--agentguide"}},"signature":"uIEhExzFwSpJwYYul+e/R/pM82rEJma6VR58QreG7wda/hm+cz/xgbHd8wzDxz7udeK4Hp0X5MtSaKgRxZ6kAw==","signedAt":"2026-06-19T18:02:01.921Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/adongwanai--agentguide","artifact":"https://unfragile.ai/adongwanai--agentguide","verify":"https://unfragile.ai/api/v1/verify?slug=adongwanai--agentguide","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}