InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now. Learn more →
Top 23 Python llm Projects
-
awesome-llm-apps
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Project mention: Show HN: AI Real Estate Agent Team (100% Open-Source with Free Tutorial) | news.ycombinator.com | 2025-08-06 -
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Project mention: Unsloth – Train LLMs 2x faster with 70% less VRAM | news.ycombinator.com | 2025-12-10 -
crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Project mention: I added native time awareness to CrewAI to fix LLM date hallucinations | news.ycombinator.com | 2025-12-14 - Project mention: “One Journey Ends, Another Begins — My Hacktoberfest 2025 Story” | dev.to | 2025-10-31
Just wrapped up my Hacktoberfest project using MindsDB and Streamlit — built a CRM Semantic Search AI app! 😄 If anyone’s into open source + AI, would love feedback on my PR: Hacktoberfest 2025 PR – Add CRM Semantic Search use case (MindsDB)
- Project mention: BettaFish – Public Opinion Sentiment Analysis Model | news.ycombinator.com | 2025-11-03
- Project mention: The AI-Native GraphDB + GraphRAG + Graph Memory Landscape & Market Catalog | dev.to | 2025-10-26
URL: https://microsoft.github.io/graphrag/ and https://github.com/microsoft/graphrag and https://github.com/Azure-Samples/graphrag-accelerator
- Project mention: Kotaemon-papers: an open-source web app to chat with your academic papers | news.ycombinator.com | 2025-01-05
Hi HN,
Our team at https://github.com/Cinnamon/kotaemon/ has been working on a public demo to showcase the new advanced citation features in our RAG (retrieval-augmented generation) application.
We’re excited to share a web app that lets users explore top daily machine learning (ML) papers on Arxiv (via the HuggingFace API) and upload their own Arxiv papers to get LLM-assisted summaries, mind maps, and answers to questions based on the content.
Some notable features:
- Instant Summaries & Mind Maps: Generate concise summaries and visual mind maps for any Arxiv paper.
- Transparent Citations: Verify AI-generated answers with clear, evidence-backed citations. Citations are highlighted directly in the in-browser PDF viewer.
- Flexible Citation Options: Choose between highlights and inline citations. Plus, click on any sentence in the AI-generated response to see its supporting source from the original paper.
- Multi-Paper Analysis: Compare, contrast, and compose summaries from multiple papers simultaneously.
- Complex Question Solving: Use Chain-of-Thought (CoT) reasoning mode to break down and solve complex questions step-by-step.
- Customizable & Private Hosting: Easily self-host or customize your private app via HuggingFace Spaces. You can securely connect your LLM and upload your own document collections.
We’d love to hear your thoughts, feedback, and recommendations as we continue improving this tool.
Check out the demo here and happy hacking!
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
gpt-researcher
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
For demonstration purposes, I'll be using the gpt-researcher tool. Github link: https://github.com/assafelovic/gpt-researcher
-
We’ll use a library called FastMCP that simplifies the process of building MCP servers. You can install it using pip:
-
-
serena
A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
Project mention: Building a 400K-Line Full-Stack App Solo with Claude Code in 2025 | dev.to | 2025-12-22Serena - Semantic code search and editing tool
-
`outlines` (https://github.com/dottxt-ai/outlines) is very good and supported by vLLM as a backend structured output provider (https://docs.vllm.ai/en/v0.8.2/features/structured_outputs.h...) for both local and remote LLMs. vLLM is probably the best open source tooling for the inference side right now.
- Project mention: Lightning.ai – an enterprise managed inference platform for AI | news.ycombinator.com | 2025-10-09
After making model training simpler with PyTorch Lightning, Lightning.AI is now tackling the next bottleneck — inference. Their new managed service targets enterprises deploying LLMs and deep learning models at scale, emphasizing performance, cost-efficiency, and developer-friendly tooling.
Platform: https://lightning.ai/
-
-
cleanlab
Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
- Project mention: You Don't Need to Spend $100/Mo on Claude Code:Your Guide to Local Coding Models | news.ycombinator.com | 2025-12-21
- Project mention: Show HN: MCP-C – cloud platform for running MCP agents and apps | news.ycombinator.com | 2025-10-28
-
-
-
-
-
transformerlab-app
Open Source Application for Advanced LLM + Diffusion Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.
Project mention: Gemma 3 QAT Models: Bringing AI to Consumer GPUs | news.ycombinator.com | 2025-04-20 - Project mention: Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents | news.ycombinator.com | 2025-09-24
We built agents to test github repo quickstarts associated with arXiv papers a couple months before this paper was published, wrote about it publicly here: https://remyxai.substack.com/p/self-healing-repos
We've been pushing it farther to implement draft PRs in your target repo, published a month before this preprint: https://remyxai.substack.com/p/paperswithprs
To limit the attack surface we added PR#1929 to AG2 so we could pass API keys to the DockerCommandLineCodeExecutor but also use egress whitelisting to block the ability of an agent to reach a compromised server: https://github.com/ag2ai/ag2/pull/1929
Since then, we've been scaling this with k8s ray workers so we can run this in the cloud to build for the hundreds of papers published daily.
By running in Docker, constraining the network interface, deploying on the cloud, and ultimately keeping humans-in-the-loop through PR review, it's hard to see where the prompt-injection attack comes into play from testing the code.
Would love to get feedback from an expert on this, can you imagine an attack scenario, Simon?
I'll need to work out a check for the case where someone creates a paper with code instructing my agent to publish keys to a public HF repo for others to exfiltrate.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020).
Python llms discussion
Python llms related posts
-
You Don't Need to Spend $100/Mo on Claude Code:Your Guide to Local Coding Models
-
Managing GitHub Copilot CLI MCP Server Configuration in Your Repository
-
I added native time awareness to CrewAI to fix LLM date hallucinations
-
OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI
-
Unsloth – Train LLMs 2x faster with 70% less VRAM
-
Show HN: Memory System for Claude Code and Other CLIs
-
Agentic Entity Resolution for Messy Product Data
- A note from our sponsor - InfluxDB www.influxdata.com | 22 Dec 2025
Index
What are some of the best open-source llm projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | awesome-llm-apps | 83,772 |
| 2 | unsloth | 49,610 |
| 3 | crewAI | 41,461 |
| 4 | MindsDB | 38,107 |
| 5 | BettaFish | 33,338 |
| 6 | graphrag | 29,803 |
| 7 | kotaemon | 24,766 |
| 8 | gpt-researcher | 24,503 |
| 9 | fastmcp | 21,322 |
| 10 | graphiti | 21,190 |
| 11 | serena | 17,340 |
| 12 | outlines | 13,141 |
| 13 | litgpt | 13,034 |
| 14 | LLMSurvey | 12,014 |
| 15 | cleanlab | 11,208 |
| 16 | llm | 10,554 |
| 17 | mcp-agent | 7,866 |
| 18 | Upsonic | 7,727 |
| 19 | OpenNMT-py | 6,981 |
| 20 | Liger-Kernel | 5,961 |
| 21 | atomic-agents | 5,387 |
| 22 | transformerlab-app | 4,592 |
| 23 | ag2 | 3,951 |
Sponsored
InfluxDB – Built for High-Performance Time Series Workloads
InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
www.influxdata.com