From f4da58fce94eb407113f8eb42a0b542aac677928 Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:43:34 +0800 Subject: [PATCH 1/7] audit: sweep AI and Agents, drop vibevoice, kittentts The AI and Agents section carried two Speech entries that fail admission, its tier order no longer matched downloads, LiteLLM was not listed under its PyPI name, and unsloth's line missed its desktop app. Downloads are PyPI last-30-day via ClickPy, fetched 2026-09-26. Removed: - vibevoice (440/month): the only PyPI release is 0.0.1 from 2025-09-26; the TTS-1.5B model is disabled after misuse and the ASR model now ships in transformers, so nothing pip-installable is maintained. - kittentts (1,917/month): the README marks it "Developer preview" (fails Stable), and PyPI kittentts is a third-party upload while the project installs from its GitHub release wheel. Also: - pydantic-ai promoted to obvious choice above crewai (5.37M vs 2.48M); crewai's pypistats monthly series swung from 28.5M in Aug to 2.4M in Sep and it requires_python <3.14, so it is now a Second Tier challenger. - claude-agent-sdk reordered above openai-agents (29.1M vs 12.1M). - LiteLLM renamed to litellm, its canonical PyPI name. - unsloth description now mentions the desktop app. - gTTS reordered above funasr by downloads (1.14M vs 282K). Co-Authored-By: Claude --- README.md | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 9f9b69cc..d4821e97 100644 --- a/README.md +++ b/README.md @@ -141,11 +141,11 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - Orchestration - [langchain](https://github.com/langchain-ai/langchain) - A framework for building agents and LLM-powered applications. - [langgraph](https://github.com/langchain-ai/langgraph) - Low-level orchestration framework for building stateful, long-running LLM agents. - - [crewai](https://github.com/crewAIInc/crewAI) - A framework for orchestrating role-playing autonomous AI agents for collaborative task solving. - [pydantic-ai](https://github.com/pydantic/pydantic-ai) - A Python agent framework for building generative AI applications with structured schemas. + - [crewai](https://github.com/crewAIInc/crewAI) - A framework for orchestrating role-playing autonomous AI agents for collaborative task solving. - Vendor Agent SDKs - - [openai-agents](https://github.com/openai/openai-agents-python) - OpenAI's framework for building and managing AI agents. - [claude-agent-sdk](https://github.com/anthropics/claude-agent-sdk-python) - Anthropic's Python SDK for building AI agents on Claude Code's harness — custom tools, in-process MCP servers, hooks. + - [openai-agents](https://github.com/openai/openai-agents-python) - OpenAI's framework for building and managing AI agents. - Personal Assistants - [hermes-agent](https://github.com/nousresearch/hermes-agent) - An adaptive personal AI assistant that grows with you. - [AstrBot](https://github.com/AstrBotDevs/AstrBot) - A multi-platform AI assistant that connects LLMs to chat apps like Telegram, Slack, and QQ, extensible with Python plugins. @@ -164,19 +164,17 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - [vllm](https://github.com/vllm-project/vllm) - A high-throughput and memory-efficient inference and serving engine for LLMs. - [mlx-lm](https://github.com/ml-explore/mlx-lm) - Run and fine-tune large language models on Apple Silicon with MLX. - LLM Gateways - - [LiteLLM](https://github.com/BerriAI/litellm) - Call 100+ LLMs using OpenAI format. + - [litellm](https://github.com/BerriAI/litellm) - Call 100+ LLMs using OpenAI format. - Image and Video Generation - [diffusers](https://github.com/huggingface/diffusers) - A library that provides pre-trained diffusion models for generating and editing images, audio, and video. - Fine-tuning - [peft](https://github.com/huggingface/peft) - A library for parameter-efficient fine-tuning of large pretrained models. - - [unsloth](https://github.com/unslothai/unsloth) - A library for faster LLM fine-tuning and training with reduced memory usage. + - [unsloth](https://github.com/unslothai/unsloth) - Faster, lower-memory LLM fine-tuning, as a Python library or a desktop app. - [axolotl](https://github.com/axolotl-ai-cloud/axolotl) - A framework for fine-tuning and post-training large language models. - Speech - [openai-whisper](https://github.com/openai/whisper) - A general-purpose automatic speech recognition model trained on 680k hours of multilingual and multitask supervised data. - - [funasr](https://github.com/modelscope/FunASR) - Industrial-grade speech recognition toolkit with speaker diarization and emotion detection. - - [vibevoice](https://github.com/microsoft/VibeVoice) - A family of open-source voice AI models from Microsoft for text-to-speech and long-form speech recognition. - [gTTS](https://github.com/pndurette/gTTS) - Python library and CLI tool for converting text to speech using Google Translate TTS. - - [kittentts](https://github.com/KittenML/KittenTTS) - Lightweight ONNX text-to-speech library with small CPU-friendly models. + - [funasr](https://github.com/modelscope/FunASR) - Industrial-grade speech recognition toolkit with speaker diarization and emotion detection. ### Deep Learning From 1e9eba4ea7b435353d708582122671c2aa9ac1e9 Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:44:18 +0800 Subject: [PATCH 2/7] feat: add mcp, minting AI and Agents > Model Context Protocol Co-Authored-By: Claude --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index d4821e97..d2cecfbf 100644 --- a/README.md +++ b/README.md @@ -146,6 +146,8 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - Vendor Agent SDKs - [claude-agent-sdk](https://github.com/anthropics/claude-agent-sdk-python) - Anthropic's Python SDK for building AI agents on Claude Code's harness — custom tools, in-process MCP servers, hooks. - [openai-agents](https://github.com/openai/openai-agents-python) - OpenAI's framework for building and managing AI agents. +- Model Context Protocol + - [mcp](https://github.com/modelcontextprotocol/python-sdk) - The official Python SDK for building Model Context Protocol servers and clients. - Personal Assistants - [hermes-agent](https://github.com/nousresearch/hermes-agent) - An adaptive personal AI assistant that grows with you. - [AstrBot](https://github.com/AstrBotDevs/AstrBot) - A multi-platform AI assistant that connects LLMs to chat apps like Telegram, Slack, and QQ, extensible with Python plugins. From ab9992cf14a1fcda3ee9882c0ff16055503e6bb0 Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:44:39 +0800 Subject: [PATCH 3/7] feat: add fastmcp to AI and Agents > Model Context Protocol Co-Authored-By: Claude --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index d2cecfbf..e61c6a2c 100644 --- a/README.md +++ b/README.md @@ -148,6 +148,7 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - [openai-agents](https://github.com/openai/openai-agents-python) - OpenAI's framework for building and managing AI agents. - Model Context Protocol - [mcp](https://github.com/modelcontextprotocol/python-sdk) - The official Python SDK for building Model Context Protocol servers and clients. + - [fastmcp](https://github.com/PrefectHQ/fastmcp) - A high-level, Pythonic framework for building MCP servers and clients. - Personal Assistants - [hermes-agent](https://github.com/nousresearch/hermes-agent) - An adaptive personal AI assistant that grows with you. - [AstrBot](https://github.com/AstrBotDevs/AstrBot) - A multi-platform AI assistant that connects LLMs to chat apps like Telegram, Slack, and QQ, extensible with Python plugins. From 6beac6c0749ad11a11b63a977d0dd3d34366c933 Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:44:53 +0800 Subject: [PATCH 4/7] feat: add google-adk to AI and Agents > Vendor Agent SDKs Co-Authored-By: Claude --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index e61c6a2c..4035871e 100644 --- a/README.md +++ b/README.md @@ -146,6 +146,7 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - Vendor Agent SDKs - [claude-agent-sdk](https://github.com/anthropics/claude-agent-sdk-python) - Anthropic's Python SDK for building AI agents on Claude Code's harness — custom tools, in-process MCP servers, hooks. - [openai-agents](https://github.com/openai/openai-agents-python) - OpenAI's framework for building and managing AI agents. + - [google-adk](https://github.com/google/adk-python) - Google's code-first toolkit for building, evaluating, and deploying AI agents. - Model Context Protocol - [mcp](https://github.com/modelcontextprotocol/python-sdk) - The official Python SDK for building Model Context Protocol servers and clients. - [fastmcp](https://github.com/PrefectHQ/fastmcp) - A high-level, Pythonic framework for building MCP servers and clients. From 4bc79bbfb269491b0fee051f15a78f33db47868b Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:45:10 +0800 Subject: [PATCH 5/7] feat: add trl to AI and Agents > Fine-tuning Co-Authored-By: Claude --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 4035871e..8cf20e0c 100644 --- a/README.md +++ b/README.md @@ -173,6 +173,7 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - [diffusers](https://github.com/huggingface/diffusers) - A library that provides pre-trained diffusion models for generating and editing images, audio, and video. - Fine-tuning - [peft](https://github.com/huggingface/peft) - A library for parameter-efficient fine-tuning of large pretrained models. + - [trl](https://github.com/huggingface/trl) - A library for post-training transformer language models with SFT, DPO, GRPO, and other trainers. - [unsloth](https://github.com/unslothai/unsloth) - Faster, lower-memory LLM fine-tuning, as a Python library or a desktop app. - [axolotl](https://github.com/axolotl-ai-cloud/axolotl) - A framework for fine-tuning and post-training large language models. - Speech From d12f0ae6309cd7fae1bfc166af7a1e45c6fd6c5b Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:45:25 +0800 Subject: [PATCH 6/7] feat: add faster-whisper to AI and Agents > Speech Co-Authored-By: Claude --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 8cf20e0c..33e8c691 100644 --- a/README.md +++ b/README.md @@ -177,6 +177,7 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents - [unsloth](https://github.com/unslothai/unsloth) - Faster, lower-memory LLM fine-tuning, as a Python library or a desktop app. - [axolotl](https://github.com/axolotl-ai-cloud/axolotl) - A framework for fine-tuning and post-training large language models. - Speech + - [faster-whisper](https://github.com/SYSTRAN/faster-whisper) - A Whisper reimplementation on CTranslate2, up to 4 times faster than openai-whisper with less memory. - [openai-whisper](https://github.com/openai/whisper) - A general-purpose automatic speech recognition model trained on 680k hours of multilingual and multitask supervised data. - [gTTS](https://github.com/pndurette/gTTS) - Python library and CLI tool for converting text to speech using Google Translate TTS. - [funasr](https://github.com/modelscope/FunASR) - Industrial-grade speech recognition toolkit with speaker diarization and emotion detection. From dfc8714afece61fe827832652129a7b63d8ae9af Mon Sep 17 00:00:00 2001 From: Vinta Chen Date: Thu, 1 Oct 2026 20:45:46 +0800 Subject: [PATCH 7/7] docs: record claude-agent-sdk and semantica audit overrides The 2026-10-01 AI and Agents audit kept claude-agent-sdk despite its Alpha classifier and semantica as a challenger without adoption-trajectory evidence, and neither override was on record in docs/audit-logs.md. Co-Authored-By: Claude --- docs/audit-logs.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/audit-logs.md b/docs/audit-logs.md index 887cec79..088c1711 100644 --- a/docs/audit-logs.md +++ b/docs/audit-logs.md @@ -28,12 +28,14 @@ Entries admitted despite the Stable quality requirement, by maintainer decision: - zensical -- admitted 2026-08-23 at version 0.0.57, PyPI classifier `Development Status :: 3 - Alpha`, with no 1.0 target announced. Admitted as a challenger displacing mkdocs because the Documentation section was carrying a dying upstream: the Material for MkDocs team's announcement of 2025-11-05 put Material into maintenance mode for twelve months and called MkDocs itself unmaintained since 2024-08 and a supply chain risk. Re-check when 1.0 lands. - openviking -- admitted 2026-08-25 (PR #3302) at version 0.4.16, PyPI classifier `Development Status :: 3 - Alpha`, with a README that said "OpenViking is still in its early stages". Admitted as a Data Layer challenger because the adoption is real: 459,446 downloads/month on pypistats (mirror-excluded) on 2026-08-24, and releases every few days. Re-check when 1.0 lands. +- claude-agent-sdk -- kept 2026-10-01 in the AI and Agents audit at version 0.2.163, PyPI classifier `Development Status :: 3 - Alpha`. Kept as a Vendor Agent SDKs obvious choice because the adoption is real: 30,033,689 downloads/month on ClickPy on 2026-10-01, up from 1.2M in March 2026 on pypistats. Re-check when 1.0 lands. ### Challenger Exceptions Entries admitted as challengers without adoption-trajectory evidence, by maintainer decision: - seleniumbase -- admitted 2026-08-16 (PR #3284) as a Browser Automation challenger. It wraps selenium, the successor trajectory in the use case belongs to playwright, and its distinct value is its stealth/UC mode. Admitted because that stealth value counts toward Browser Automation. +- semantica -- kept 2026-10-01 in the AI and Agents audit as a Data Layer challenger at 16,582 downloads/month on ClickPy, with no adoption-trajectory evidence found. Kept by maintainer decision. ### Mature-stable Keeps