Search Results for "web-based" - Page 30
Sort By:
Showing 7075 open source projects for "web-based"
View related business solutions-
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.
-
Stop vibe-debugging.AppSignal's MCP server hands Claude, Cursor, or Zed your real errors, traces, and the deploy that shipped them. AI writes the fix; you review the diff.
-
1
Build Your Own OpenClaw
A step-by-step guide to build your own AI agent
...The project is structured into 18 progressive stages, each introducing a new concept such as tool usage, memory persistence, event-driven design, and multi-agent coordination, with each step including both explanatory documentation and runnable code. It begins with foundational concepts like conversational loops and tool integration, then expands into more advanced capabilities such as dynamic skill loading, web interaction, and context management. As the tutorial progresses, it introduces architectural improvements including event-driven systems, WebSocket communication, and configuration hot-reloading to support scalability and real-time interaction. -
2
Harbor LLM
Run a full local LLM stack with one command using Docker
...With a single command, users can start preconfigured tools like Ollama and Open WebUI, enabling chat, workflows, and integrations immediately. Harbor supports multiple inference engines, including llama.cpp and vLLM, and connects them seamlessly to user interfaces. It also includes tools for web retrieval, image generation, voice interaction, and workflow automation. Built on Docker, Harbor allows services to run in isolated containers while communicating over a local network. It is intended for local development and experimentation rather than production deployment, giving developers a flexible way to explore AI systems, test configurations, and manage complex LLM stacks without manual wiring or setup overhead. -
3
Pal
A personal context-agent that learns how you work
...Instead of acting as a simple chatbot, Pal continuously builds a structured database of a user’s knowledge and context so it can answer questions, recall information, and assist with future tasks more effectively. The agent can perform web research, summarize information, and store insights so that useful discoveries are not lost across conversations or sessions. Over time, the agent learns from interactions, remembers patterns that worked well, and applies those learnings to similar tasks in the future, allowing it to improve without requiring additional model training. -
4
PokeeResearch-7B
Pokee Deep Research Model Open Source Repo
PokeeResearchOSS provides an open-source, agentic “deep research” model centered on a 7B backbone that can browse, read, and synthesize current information from the web. Instead of relying only on static training data, the agent performs searches, visits pages, and extracts evidence before forming answers to complex queries. It is built to operate end-to-end: planning a research strategy, gathering sources, reasoning over conflicting claims, and writing a grounded response. The repository includes evaluation results on multi-step QA and research benchmarks, illustrating how web-time context boosts accuracy. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
cheat.sh
The only cheat sheet you need
cheat.sh is a compact, network-accessible cheat-sheet service that serves concise examples and usage notes for hundreds of shell commands, programming languages, and tools via a simple HTTP interface. You can query it from the terminal (for example curl cht.sh/rsync or curl cheat.sh/ls) or browse the web front page; it also supports a shorthand hostname (cht.sh) and provides both online and standalone/local installation modes. The repository contains the server and client code, instructions to run a local standalone instance (including Python virtualenv setup), and tooling to fetch or maintain the upstream cheat-sheet data; installation documentation explains disk-space needs and dependency setup for offline use. ... -
6
Procrastinate
PostgreSQL-based Task Queue for Python
Procrastinate is a powerful PostgreSQL-based task queue for Python, built to integrate seamlessly with Django and FastAPI. It allows you to schedule and execute background jobs using your existing database infrastructure, avoiding the need for additional queueing systems like Redis. Procrastinate is designed with simplicity, reliability, and observability in mind. -
7
pywinauto
Windows GUI Automation with Python (based on text properties)
pywinauto is a set of Python modules to automate the Microsoft Windows GUI. At its simplest it allows you to send mouse and keyboard actions to Windows dialogs and controls, but it has support for more complex actions like getting text data. -
8
Throttled
Workaround for Intel throttling issues in Linux
This tool was originally developed to fix Linux CPU throttling issues affecting Lenovo T480 / T480s / X1C6. The CPU package power limit (PL1/2) is forced to a value of 44 W (29 W on battery) and the temperature trip point to 95 'C (85 'C on battery) by overriding default values in MSR and MCHBAR every 5 seconds (30 on battery) to block the Embedded Controller from resetting these values to default. On systems where the EC doesn't reset the values (ex: ASUS Zenbook UX430UNR), the power limit... -
9
wger
Self hosted FLOSS fitness/workout, nutrition and weight tracker
wger Workout Manager is a free and open web application that manages your exercises, routines and nutrition. It started out as a personal project to replace my growing collection of spreadsheets but has turned into something that other people may find useful. You can create and manage flexible training routines for whatever goals you have. Select exactly what exercises you are going to do and how many repetitions, time or distance you want to do. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Tenacity Python
Retrying library for Python
Tenacity is a Python library that enables automatic retrying of functions with customizable strategies. It replaces the now-deprecated retrying library and supports exponential backoff, fixed delays, stop and wait conditions, and exception filtering. Useful for network operations, API calls, or any unstable process, Tenacity helps increase reliability in Python applications by handling transient failures gracefully and robustly. -
11
Text Generation Inference
Large Language Model Text Generation Inference
Text Generation Inference is a high-performance inference server for text generation models, optimized for Hugging Face's Transformers. It is designed to serve large language models efficiently with optimizations for performance and scalability. -
12
OpenClaw Medical Skills
The largest open-source medical AI skills library for OpenClaw
...The project organizes domain-specific “skills” that enable autonomous agents to perform tasks related to biomedical research, healthcare analysis, and clinical data interpretation. Each skill is packaged as a modular component that can be integrated into an OpenClaw-based AI assistant, allowing the agent to perform expert-level reasoning and workflows in medical contexts. Instead of relying on general-purpose language model responses, the repository equips AI agents with structured instructions and tools tailored to medical knowledge and datasets. This modular design allows developers and researchers to build AI systems that can access specialized medical reasoning processes, retrieve relevant biomedical information, and generate structured outputs suitable for analysis or downstream processing. -
13
Claude Code Bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini
Claude Code Bridge is an open-source command-line tool designed to enable real-time collaboration between multiple AI coding assistants within a unified development environment. The system allows developers to coordinate interactions between models such as Claude, Codex, and Gemini so that they can work together on programming tasks. By maintaining persistent shared context between these models, the tool reduces redundant prompts and minimizes token usage while allowing each AI system to... -
14
Timesketch
Collaborative forensic timeline analysis
...The system supports tagging, sketch notes, and story building so teams can annotate findings and share context without losing the raw data trail. Integrations with popular DFIR pipelines make ingestion repeatable, while role-based access and audit logs support enterprise workflows. By combining scale, collaboration, and reproducibility, Timesketch moves incident response beyond ad-hoc spreadsheets to a durable, team-oriented investigation record. -
15
GTFOBins
GTFOBins is a curated list of Unix binaries
GTFOBins is a curated catalog of Unix / POSIX system binaries and how they can be misused to bypass restrictions, escalate privileges, exfiltrate data, spawn shells, or otherwise act as “living off the land” tools in a compromised environment. It collects documented techniques for how everyday binaries (e.g. awk, bash, tar, scp) can be abused under constrained conditions. Indexed list of Unix binaries and documented misuse techniques. Examples of command invocations to exploit... -
16
KServe
Standardized Serverless ML Inference Platform on Kubernetes
KServe provides a Kubernetes Custom Resource Definition for serving machine learning (ML) models on arbitrary frameworks. It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX. It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and... -
17
Argilla
The open-source data curation platform for LLMs
...Deploy your own Argilla Server on Spaces with a few clicks. Use embeddings to find the most similar records with the UI. This feature uses vector search combined with traditional search (keyword and filter based). Argilla is free, open-source, and 100% compatible with major NLP libraries (Hugging Face transformers, spaCy, Stanford Stanza, Flair, etc.). In fact, you can use and combine your preferred libraries without implementing any specific interface. Most annotation tools treat data collection as a one-off activity at the beginning of each project. ... -
18
PyG
Graph Neural Network Library for PyTorch
...In addition, it consists of easy-to-use mini-batch loaders for operating on many small and single giant graphs, multi GPU-support, DataPipe support, distributed graph learning via Quiver, a large number of common benchmark datasets (based on simple interfaces to create your own), the GraphGym experiment manager, and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds. All it takes is 10-20 lines of code to get started with training a GNN model (see the next section for a quick tour). -
19
Databend
Cloud-native open source data warehouse for analytics and AI queries
...This architecture enables cost-efficient storage and elastic scaling for workloads that involve large datasets and complex queries. Databend provides a unified engine capable of handling analytics, vector search, and full-text search within a single platform. Databend supports SQL-based workflows and enables real-time data ingestion, transformation, and analysis through streaming and task orchestration features. With its cloud-native design and distributed architecture, Databend can run both as a self-hosted system or within managed environments to power data analytics, AI workloads, and large-scale data. -
20
Pixeltable
Data Infrastructure providing an approach to multimodal AI workloads
...Unlike traditional architectures that require multiple tools such as databases, vector stores, and workflow orchestrators, Pixeltable unifies these functions within a table-based abstraction. Developers define data transformations and AI operations using computed columns on tables, allowing pipelines to evolve incrementally as new data or models are added. The framework supports multimodal content including images, video, text, and audio, enabling applications such as retrieval-augmented generation systems, semantic search, and multimedia analytics. -
21
Torch Pruning
DepGraph: Towards Any Structural Pruning
...The library focuses on reducing the size and computational cost of neural networks by removing redundant parameters and channels while maintaining model performance. It introduces a graph-based algorithm called DepGraph that automatically identifies dependencies between layers, allowing parameters to be pruned safely across complex architectures. This dependency analysis makes it possible to prune large networks such as transformers, convolutional networks, and diffusion models without breaking the computational graph. ... -
22
ThetaGang
ThetaGang is an IBKR bot for collecting money
...The strategy, as implemented here, does a few things differently from the one described in the post above. For one, it's intended to be used to augment a typical index-fund-based portfolio with specific asset allocations. For example, you might want to use a 60/40 portfolio with SPY (S&P500 fund) and TLT (20-year treasury fund). This strategy reduces risk, but may also limit gains from big market swings. By reducing risk, one can increase leverage. ThetaGang will try to acquire your desired allocation of each stock or ETF according to the weights you specify in the config. ... -
23
FATE
An industrial grade federated learning framework
FATE (Federated AI Technology Enabler) is the world's first industrial grade federated learning open source framework to enable enterprises and institutions to collaborate on data while protecting data security and privacy. It implements secure computation protocols based on homomorphic encryption and multi-party computation (MPC). Supporting various federated learning scenarios, FATE now provides a host of federated learning algorithms, including logistic regression, tree-based algorithms, deep learning and transfer learning. FATE became open-source in February 2019. FATE TSC was established to lead FATE open-source community, with members from major domestic cloud computing and financial service enterprises. ... -
24
jetson-stats
Simple package for monitoring and control your NVIDIA Jetson
jetson_stats is a Python package for monitoring and controlling NVIDIA Jetson boards. It supports Jetson platforms such as Orin, Xavier, Nano, TX, and newer Jetson families. The project includes jtop, a terminal-based dashboard that gives users a live view of CPU, GPU, memory, power, temperature, engine usage, and system status. It can also be imported into Python scripts, which makes it useful for custom monitoring, robotics dashboards, automation, and diagnostics. Developers working with embedded AI systems can use it to understand performance limits and troubleshoot hardware behavior during deployment. ... -
25
RKN Block Checker
Diagnose RKN/TSPU internet blocks layer by layer (DNS, TCP, TLS, HTTP)
...It tests blocking behavior layer by layer instead of only reporting that a site is unreachable. The tool can help distinguish DNS poisoning, TCP reset behavior, TLS DPI based on SNI, and ISP stub pages. This makes it useful for developers, system administrators, network researchers, and censorship-measurement workflows. It is designed as a console utility with straightforward installation and optional proxy support. Its main value is giving users a structured way to understand what kind of network interference is occurring rather than relying on vague connectivity symptoms.
