Source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/emcie-co/parlant
Markdown source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/emcie-co/parlant.md
Description: ai-agent-book and parlant share 17 technologies: React, uvicorn, FastAPI, OpenAI, fastmcp, Vite, Rich, authlib, MCP, tiktoken, structlog, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, Lucide, and remark-gfm. Both are written in Python.

# ai-agent-book vs parlant

ai-agent-book and parlant share 17 technologies: React, uvicorn, FastAPI, OpenAI, fastmcp, Vite, Rich, authlib, MCP, tiktoken, structlog, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, Lucide, and remark-gfm. Both are written in Python.

- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book): 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
- [emcie-co/parlant](https://seerepo.com/r/emcie-co/parlant): Parlant is an open platform for building customer-facing chat agents with AI. Describe how the agent should behave, and your coding agent implements it for you.

## What they share and what sets them apart

- In common: React, uvicorn, FastAPI, OpenAI, fastmcp, Vite, Rich, authlib, MCP, tiktoken, structlog, Tailwind CSS, class-variance-authority, tailwind-merge, Radix UI, Lucide, remark-gfm
- Only in ai-agent-book: azure-search-documents, azure-storage-blob, chromadb, psycopg2-binary, Postgres, pyarrow, Anthropic, Hugging Face, Google, PostHog, Flask, anyio, AIOHTTP, Next.js, Express, Astro, mkdocs-material, matplotlib, seaborn, Plotly, google-auth, google-auth-httplib2, google-auth-oauthlib, pyotp, accelerate, bitsandbytes, cut-cross-entropy, faiss-cpu, lightgbm, mem0ai, nltk, openai-whisper, scikit-image, sentencepiece, triton, xformers, torch, transformers, peft, datasets, litellm, Ollama, scikit-learn, rank-bm25, groq, librosa, trl, snac, torchaudio, opencv-python, sentence-transformers, langchain-openai, mlx-audio, vLLM, lxml, python-magic, torchcodec, xlrd, xlsxwriter, beautifulsoup4, pillow, python-pptx, pypdf2, reportlab, html2text, pypdf, python-docx, openpyxl, markdown, pdfplumber, pymupdf, sendgrid, youtube-transcript-api, yt-dlp, Pydantic, loguru, psutil, pptxgenjs, sharp, D3, recharts, onnxruntime-node, react-syntax-highlighter, react-markdown, katex
- Only in parlant: starlette, aiosqlite, SQLite, nano-vectordb, keyring, tokenizers, jinja2, jsonschema, openapi3-parser, coloredlogs, OpenTelemetry, opentelemetry-instrumentation, boto3, next-themes, sonner, react-resizable-panels, CodeMirror, TanStack, vaul, rehype-highlight, rehype-raw, streamdown

## Side by side

| | ai-agent-book | parlant |
|---|---|---|
| Size | 422,447 lines written, 1,067 code files | 214,893 lines written, 334 code files |
| Who writes it | 20.8% of its commits signed by AI. With Claude Code | 1.1% of its commits signed by AI. With Claude Code, Codex, and GitHub Copilot |
| Activity | Last push October 8, 2026, 1,610 commits, 57,240 stars | Last push November 6, 2026, 5,148 commits, 18,325 stars |
| Tests | 624 test files. 34.3% of its code files have a test that imports them | 257 test files. 57.5% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, ai-agent-book or parlant?

ai-agent-book, with 422,447 lines written; parlant has 214,893.

The proof: [bojieli/ai-agent-book's code at commit dbc046e](https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)

### Which has more GitHub stars, ai-agent-book or parlant?

ai-agent-book, with 57,240 stars; parlant has 18,325.

The proof: [bojieli/ai-agent-book on GitHub](https://github.com/bojieli/ai-agent-book)

### Which has more tests, ai-agent-book or parlant?

ai-agent-book, with 624 test files; parlant has 257.

The proof: [bojieli/ai-agent-book's code at commit dbc046e](https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)

### Which was updated more recently, ai-agent-book or parlant?

parlant: its last push was on November 6, 2026, and ai-agent-book's on October 8, 2026.

The proof: [emcie-co/parlant's commits on GitHub](https://github.com/emcie-co/parlant/commits)

### Which has more commits signed by AI, ai-agent-book or parlant?

ai-agent-book: an AI signed 20.8% of its commits, with Claude Code; in parlant, 1.1%.

The proof: [the commits each tool signed in bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/ai)

## Sources

- bojieli/ai-agent-book: Read on November 5, 2026, at commit dbc046e (https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)
- emcie-co/parlant: Read on November 6, 2026, at commit a071a81 (https://github.com/emcie-co/parlant/tree/a071a81406e47b4a0ae3bfd448e4deb170ac2f4b)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.