Search Results for "main"
Sort By:
Showing 97 open source projects for "main"
View related business solutions-
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
BERTopic
Leveraging BERT and c-TF-IDF to create easily interpretable topics
...However, that takes quite some time and lacks a global representation. Instead, we can visualize the topics that were generated in a way very similar to LDAvis. By default, the main steps for topic modeling with BERTopic are sentence-transformers, UMAP, HDBSCAN, and c-TF-IDF run in sequence. -
2
Agent Reach
Give your AI agent eyes to see the entire internet
...It can be useful for research agents, automation workflows, competitive monitoring, content analysis, and social listening. Agent-Reach also supports modern agent environments by exposing capabilities that can be connected into larger AI workflows. Its main value is making scattered web platforms easier for agents to query, inspect, and summarize from the command line. -
3
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. AirLLM preprocesses model weights so that each transformer layer can be loaded independently during computation, reducing the memory footprint while still performing full inference. ... -
4
ChatRWKV
ChatRWKV is like ChatGPT but powered by RWKV
...It connects to the broader RWKV ecosystem, including newer RWKV model versions and compatible weights. ChatRWKV is useful for developers who want to test RWKV as a practical conversational model rather than only as a research architecture. Its main value is showing how RWKV can be applied to chatbot-style interfaces while preserving the speed and memory benefits of its model design. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...The project explores the idea that instead of stacking hundreds of unique transformer layers, a smaller set of layers can be reused iteratively during inference to achieve deeper reasoning without increasing parameter count. It divides computation into three main stages, including a pre-processing phase, a looped recurrent reasoning block, and a final output refinement stage, creating a structured pipeline for inference. The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. ... -
6
Pyro
Deep universal probabilistic programming with Python and PyTorch
Pyro is a flexible, universal probabilistic programming language (PPL) built on PyTorch. It allows for expressive deep probabilistic modeling, combining the best of modern deep learning and Bayesian modeling. Pyro is centered on four main principles: Universal, Scalable, Minimal and Flexible. Pyro is universal in that it can represent any computable probability distribution. It scales easily to large datasets with minimal overhead, and has a small yet powerful core of composable abstractions that make it both agile and maintainable. Lastly, Pyro gives you the flexibility of automation when you want it, and control when you need it. -
7
AI Infra
Understanding of AI Infra: Quantitative Analysis and System Design
...The source is written in Markdown and automatically built into a XeLaTeX PDF and a searchable website. Research notes, references, calculation scripts, and historical revisions are preserved alongside the main manuscript. -
8
Google Antigravity SDK
Python library for building agents that leverages Google Antigravity
...It supports streaming responses, stateful sessions, custom Python tools, MCP server integration, hooks, policies, and event-driven triggers. The package relies on a compiled runtime binary distributed through platform-specific PyPI wheels, so installation from PyPI is required for normal use. Its main value is giving developers a structured Python framework for creating local, tool-using, multimodal, policy-controlled AI agents. -
9
whichllm
Find the local LLM that actually runs and performs best
...It focuses on real, recency-aware benchmarks so recommendations better reflect current model performance. whichllm is especially helpful for developers, AI hobbyists, and researchers comparing local inference options across NVIDIA, AMD, Apple Silicon, and CPU-only environments. Its main value is reducing guesswork when choosing a local model to download and run. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
10
CodiumAI PR-Agent
AI-Powered tool for automated pull request analysis
CodiumAI PR-Agent is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of commands. See the Usage Guide for instructions how to run the different tools from CLI, online usage, Or by automatically triggering them when a new PR is opened. You can try GPT-4 powered PR-Agent, on your public GitHub repository, instantly. Just mention @CodiumAI-Agent and add the desired command in... -
11
Chatterbox TTS Server
Self-host the powerful Chatterbox TTS model
...It also includes OpenAI-compatible API behavior, which helps developers connect it to existing tools that already expect that style of endpoint. The server can run on NVIDIA CUDA, AMD ROCm, or CPU, giving it flexibility across different hardware setups. Its main value is packaging a powerful TTS workflow into a practical service that can be accessed through a browser or integrated into other software. -
12
BrowserGym
A Gym environment for web task automation
...It is intended for researchers building web agents rather than for end users looking for a consumer automation product. The project provides a common environment where agents can interact with websites, execute tasks, and be evaluated against standardized benchmarks. One of its main strengths is that it bundles several important benchmarks by default, including MiniWoB, WebArena, VisualWebArena, WorkArena, AssistantBench, WebLINX, and OpenApps. This gives researchers a unified way to compare agent behavior across diverse web environments and task types without stitching together separate evaluation stacks. BrowserGym is also designed to be extensible, and the repository notes that creating new benchmarks mainly involves inheriting its abstract task interface. -
13
MagicTime
Time-lapse Video Generation Models as Metamorphic Simulators
This repository is the official implementation of MagicTime, a metamorphic video generation pipeline based on the given prompts. The main idea is to enhance the capacity of video generation models to accurately depict the real world through our proposed methods and dataset. Compared to general videos, metamorphic videos contain physical knowledge, long persistence, and strong variation, making them difficult to generate. -
14
ElevenLabs Python
The official Python SDK for the ElevenLabs API
...The library wraps the HTTP API into a typed Python client, so you can perform text-to-speech, streaming, voice cloning, voice management, and agents-related operations with simple method calls. It exposes ElevenLabs’ main models such as Eleven Multilingual v2, Eleven Flash v2.5, and Eleven Turbo v2.5, each targeting different trade-offs between latency, cost, and quality. The SDK is designed for quick setup: after installing the package and setting an API key, you can generate speech in multiple languages and play or process the resulting audio bytes. ... -
15
AgentHandover
AgentHandover observes, learns and teaches agents with skills
...The project supports both focused recording for specific tasks and passive discovery for workflows that appear repeatedly over time. It stores learned knowledge locally and uses feedback from later executions to improve confidence, add decision branches, and demote stale or failing skills. Its main value is helping agents learn how a person actually works, so recurring tasks can be handed off with more context, consistency, and trust. -
16
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. Both models use a native MXFP4 quantization for efficient memory use and support OpenAI’s Harmony response format, enabling transparent full chain-of-thought reasoning and advanced tool integrations such as function calling, browsing, and Python code execution. ... -
17
MathCode
A Frontier Mathematical Coding Agent
...It supports an agentic proving workflow where the system behaves more like an interactive mathematical engineer than a one-shot text generator. MathCode also includes visualization-oriented tooling such as theorem graph generation for Obsidian knowledge workflows. Its main value is bridging natural-language mathematics with formal verification systems in a way that is more automated, inspectable, and iterative than traditional theorem-proving pipelines. -
18
Harness-1
Ultra Recipe for Training Long-Horizon Search Agents
...This lets the policy focus on higher-level decisions instead of trying to keep every detail inside the model context. The repository includes inference utilities, training scripts, evaluation runners, dataset tools, and documentation for running the released checkpoint. Its main value is showing how a smaller open model can approach advanced search-agent behavior through structured retrieval state and reinforcement learning. -
19
Future AGI
Open-source platform for evaluating, observing, and improving LLM
...It supports both cloud and self-hosted deployment models, making it useful for teams with different privacy, infrastructure, and compliance needs. Future AGI is especially relevant for agent-heavy products where reliability, regression testing, and safety checks matter before and after release. Its main value is turning AI agent development into a measurable engineering process instead of an informal cycle of prompting, guessing, and manual review. -
20
OpenMed
Open source healthcare AI
...The project includes a curated registry of more than a dozen medical NER models focused on areas such as diseases, drugs, anatomy, genes, and protected health information, and it is built to support both research and deployment scenarios. OpenMed can be used in three main ways: as a simple Python API for scripts and notebooks, as a Docker-friendly FastAPI service for backend integration, and as a batch-processing system for multi-document workflows. -
21
DFlash
Block Diffusion for Ultra-Fast Speculative Decoding
DFlash is an open-source framework for ultra-fast speculative decoding using a lightweight block diffusion model to draft text in parallel with a target large language model, dramatically improving inference speed without sacrificing generation quality. It acts as a “drafter” that proposes likely continuations which the main model then verifies, enabling significant throughput gains compared to traditional autoregressive decoding methods that generate token by token. This approach has been shown to deliver lossless acceleration on models like Qwen3-8B by combining block diffusion techniques with efficient batching, making it ideal for applications where latency and cost matter. ... -
22
Ollama RAG Chatbot
Chat with multiple PDFs locally
...Model support is flexible, with compatibility for both Hugging Face models and Ollama-based models, and the interface is delivered through Gradio for a lightweight user experience. The main value of the project is its ability to process multiple PDF inputs and turn them into a question-answering workflow centered on document retrieval. With Docker support, script-based setup, optional ngrok exposure, and a clear local run path, it serves as a compact starter project for people who want a hands-on, self-hosted PDF chat system. -
23
Kornia
Open Source Differentiable Computer Vision Library
Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by existing packages, this library is composed by a subset of packages containing operators that can be inserted within neural networks to train models to perform image transformations, epipolar geometry, depth estimation, and low-level image processing such as filtering and edge detection that operate directly on tensors. ... -
24
Vision Agents
Open Vision Agents by Stream. Build voice and vision agents quickly
...It supports use cases such as live coaching, telehealth, customer support, security monitoring, interactive video assistants, and voice-controlled tools. Vision Agents is model-agnostic, so developers can connect providers such as OpenAI, Gemini, Claude, Hugging Face, YOLO, Roboflow, and others. Its main value is giving developers a flexible foundation for multimodal agents that operate on live audio and video instead of only static prompts. -
25
Ideogram 4
Open image model at the forefront of design
...It can also accept plain-text prompts, making it accessible to users who prefer a simpler generation style. Ideogram 4 is especially useful for design-heavy outputs such as posters, ads, mockups, branded graphics, and images that include readable text. Its main value is combining open model access with professional-level control over image structure and visual direction.
