Search Results for "agent based" - Page 37
Sort By:
Showing 935 open source projects for "agent based"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
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.
-
1
-
2
-
3
-
4
-
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.
-
5
Nemotron 3 Super
Open language model developed by NVIDIA as part of Nemotron-3 family
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 is a large-scale open language model developed by NVIDIA as part of the Nemotron-3 family of generative AI systems designed for advanced reasoning, conversational interaction, and agent-based workflows. The model contains approximately 120 billion parameters, but employs a Mixture-of-Experts architecture that activates only a smaller subset of parameters during inference, improving computational efficiency while maintaining high capability. Its architecture combines Transformer attention layers with Mamba state-space components to balance long-context reasoning, memory efficiency, and high-quality language generation. ... -
6
MiniMax-M2.7
Self-evolving AI model for agents, coding, and complex workflows
MiniMax-M2.7 is a large-scale open-weight language model designed for advanced agent-based workflows, professional software engineering, and complex productivity tasks. With 229B parameters, it introduces a self-evolution framework in which the model actively improves its own capabilities by updating memory, generating skills, and iterating through reinforcement learning experiments. This process enables it to autonomously refine systems, achieving measurable performance gains such as a 30% improvement in programming scaffolds. ... -
7
Hy3 preview
Efficient MoE model for reasoning, coding, and AI agent workflows
Hy3 preview is Tencent Hunyuan’s latest open-weight Mixture-of-Experts language model, designed for advanced reasoning, coding, instruction following, and autonomous agent workflows. It is the first model built on Tencent’s rebuilt training infrastructure and introduces significant improvements in context learning, software engineering, and tool-based task execution. The model features 295B total parameters with only 21B activated during inference, plus a dedicated 3.8B Multi-Token Prediction (MTP) layer that accelerates generation through speculative decoding. ... -
8
...Games are started as the user who owns them. So the agent will see that a given Gaming server is started by the owning user. It will launch the game server as the user. This is also useful if admins enforce some kind of user based qutoa policy like disk quota or ulimit settings in Linux/Unix. Installations can be cloned from the web interface. Steam based games can be installed or updated using the steam client from the we
-
9
Trading Agent Competition (TAC) is an international forum designed to promote and encourage high quality research into the trading agent problem. The TAC SCM open-source software consists of a Java-based Game Server and and library for developing agents.
-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
SimForge is a web-based Agent Based Model of an Open Source Ecosystem implemented in Python with Django. Developers act on randomly drawn preferences to create, collaborate, and use software.
-
11
Skill based routing application, based on Asterisk. Uses asterisk-java for Asteriek connection. Includes a web-based agent desktop.
-
12
DeepSeek-V4-Pro
Flagship MoE model for advanced reasoning, coding, and agents
DeepSeek-V4-Pro is a flagship open-weight Mixture-of-Experts language model designed for high-performance reasoning, coding, and agent-based workflows at scale. It features approximately 1.6 trillion total parameters with around 49B activated during inference, enabling strong efficiency while maintaining frontier-level capability. The model supports an ultra-long context window of up to 1 million tokens, making it highly suitable for long-document reasoning, large codebases, and complex multi-step tasks. ... -
13
Hexabot v2
Hexabot is an open-source AI chatbot / agent builder.
Hexabot v2 is an open-source AI chatbot / agent solution. It allows you to create and manage multi-channel, and multilingual chatbots / agents with ease. Hexabot is designed for flexibility and customization, offering powerful text-to-action capabilities. Originally a closed-source project (version 1), we've now open-sourced version 2 to contribute to the community and enable developers to customize and extend the platform with extensions. -
14
The project is a case implemntation for a Multiple Agent Web Based System. The case is concerned with Teaching and Learning.
-
15
Pluster is a cluster management software developed with python. It is easy to install and maintain. Pluster Provides cluster performance monitoring and remote OS installing. It's future will be an agent-based management system.
-
16
fluxychat
Realtime chat API on Cloudflare — hosted or self-host
FluxyChat is a multi-tenant realtime chat API built on Cloudflare Workers, Durable Objects, and D1. What's different: - One Durable Object per room: WebSocket fan-out + ordering at the edge, no socket fleet to manage - Agent tool calls stream on the same room WebSocket as chat messages — debuggable in the operator console - MIT self-host on your own Cloudflare account, or use the hosted beta - Next.js operator console: rooms, agents, billing hooks out of the box - @fluxy-chat/sdk:... -
17
SeSAm (Shell for Simulated Agent Systems) provides a generic environment for modelling and experimenting with agent-based simulation with a special focus on the easy construction of complex models including dynamic interdependencies or emergent behaviour
-
18
This is an education software intended to teach the basic data structures like staks, queues, trees and graphs. The software use an tutorial intelligent agent to keep track of the status of the student.
-
19
JACOB stands for [J]ava [A]gent [C]ontainer [OB]jects. Its purpose is to provide a framerwork for developing Agent Applications (by plugins). Applicability in the domain of distributed computing, decentralized job scheduling and simple P2P frameworks.
-
20
Devstral 2
Agentic 123B coding model optimized for large-scale engineering
...Devstral 2 supports a 256k context window, enabling deep understanding of large repositories, long diffs, and extended technical discussions. It integrates seamlessly with agent frameworks and developer tools, including the Mistral Vibe CLI, enabling terminal-based automation and interactive development workflows. -
21
-
22
Open Source SIP Back to Back User Agent) and Billing system. Has an Embeded TCL interpreter making session control and session mediation limitless in flexibility. Useful for: Routing Engine, Calling Cards, SBC, Peering, Wholesale and more!
-
23
GASPAR implements an dialectical argumentation framework for instantiating the artificial intellect of a software agent. In this artilect, motivations are represented in mental faculties which argue why and how these motivations can be adopted.
-
24
lastest
AI-supported visual verification and tests you can actually trust.
Lastest.cloud is a free, open-source verification of development, self-hosted visual regression and end-to-end testing platform for web applications. An AI agent records you clicking through your running app and generates Playwright tests with multi-selector fallback. Replays are deterministic and token-free, so your CI/CD bill doesn't scale with your test suite. Lastest ships three diff engines side-by-side — pixel (pixelmatch), structural (SSIM), and perceptual (Butteraugli) — so... -
25
Hunyuan-A13B-Instruct
Efficient 13B MoE language model with long context and reasoning modes
...While the total model includes 80 billion parameters, only 13 billion are active per forward pass, making it highly efficient while maintaining strong performance across benchmarks. It supports up to 256K context tokens, advanced reasoning (CoT) abilities, and agent-based workflows with tool parsing. The model offers both fast and slow thinking modes, letting users trade off speed for deeper reasoning. It excels in mathematics, science, coding, and multi-turn conversation tasks, rivaling or outperforming larger models in several areas. Deployment is supported via TensorRT-LLM, vLLM, and SGLang, with Docker images and integration guides provided. ...