AI agent starters · Rank #85
xunlong
Grade F: derived only from the two verdicts below. How grades work
多模态内容创作系统 - 报告、小说、演示文稿
Why this verdict
How we check →- No commits in 90 days; last commit 373 days ago. receipt ↗
- OpenAI SDK 1 declared; latest is 3 (2 majors behind). receipt ↗
- LangChain 0 declared; latest is 1 (1 major behind). receipt ↗
- On current major: Pydantic. receipt ↗
- Not counted in verdict: Anthropic SDK 0 → 1, FastAPI 0 → 0, LangGraph 0 → 1. receipt ↗
Snapshot: commit f1f9364 on master, checked 2026-10-19 07:30 UTC. Receipts link to files at this exact commit.
- Two or more breaking releases behind on a core dependency.
Dependency freshness
| Package | Declared | Latest | Status |
|---|---|---|---|
| OpenAI SDK openai | 1.0.0 | 3.35.1 | 2 majors behind |
| Anthropic SDK anthropic | 0.25.0 | 1.15.0 | Behind, not counted |
| FastAPI fastapi | 0.100.0 | 0.146.0 | Behind, not counted |
| LangChain langchain | 0.1.0 | 1.4.6 | 1 major behind |
| LangGraph langgraph | 0.0.40 | 1.2.16 | Behind, not counted |
| Pydantic pydantic | 2.0.0 | 2.14.1 | Current |
Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.
What's in the stack
- Framework
- FastAPI
- API layer
- Pydantic, Uvicorn
- Testing
- pytest
Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.
What the README says you get
- AIMulti-agent orchestration
Agent orchestration based on LangGraph with task decomposition and parallel execution
- AIMultiple LLM providers
Configure multiple LLM providers in `config/llm_config.yaml`
- AnalyticsLangFuse observability
Integrated with LangFuse for full-process tracking and monitoring
- APIAutomated web search
Automated web search, content extraction, and knowledge integration
- APISearch engine configuration
Configure search behavior in `config/search_config.yaml`
- ContentReport, fiction, PPT modes
Supports Report, Fiction, and PPT generation modes
- ContentMulti-format export
Supports Markdown, HTML, PDF, DOCX, PPTX formats
- ContentStyle customization
Multiple writing and presentation styles
- ContentSpeaker notes generation
Use `--speech-notes` to generate speaker notes for each slide
- ContentCustom export templates
HTML templates in `templates/` directory support customization
Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote; 2 unverifiable items were discarded. A README claim is the maker's description, not something we tested.
Watch xunlong
Get told if it goes dormant, gets archived, falls further behind on a core dependency, or changes its license or price.
History
Sep 29, 2026 → Oct 19, 2026. One square per check, colored by maintenance status. Hover for details.
Show as a table
| Date | Maintenance | Dependencies | Commits (90d) |
|---|---|---|---|
| Oct 19, 2026 | Dormant | 2+ majors behind | 0 |
| Oct 12, 2026 | Dormant | 2+ majors behind | 0 |
| Sep 29, 2026 | Dormant | 2+ majors behind | 0 |
Sources
Every claim on this page comes from these public records, checked . Open them to verify.
- Commit history ↗ default branch (master) at the checked commit: pulse, contributors, last commit
- Releases ↗ latest release
- requirements.txt ↗ declared dependency versions and stack (at commit f1f9364)
- README ↗ quoted features at the checked commit
- PyPI ↗ latest versions of Python packages (each linked in the table above)