Search Results for "tuning"
Sort By:
Showing 17 open source projects for "tuning"
View related business solutions-
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.
-
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.
-
1
InstantCharacter
Personalize Any Characters with a Scalable Diffusion Transformer
InstantCharacter is a tuning-free diffusion transformer framework created by Tencent Hunyuan / InstantX team, which enables generating images of a specific character (subject) from a single reference image, preserving identity and character features. Uses adapters, so full fine-tuning of the base model is not required. Demo scripts and pipeline API (via infer_demo.py, pipeline.py) included. -
2
Overmind
The platform for continuously improving AI agents
...OpenTelemetry traces can be converted into versioned evaluation and training datasets tied to those capabilities. The platform runs evaluations, prompt and control-flow experiments, and fine-tuning workflows against real agent behavior. Resulting models can be benchmarked, deployed, rolled back, or accessed through one OpenAI-compatible inference API. Developers can use the web console, CLI, REST API, or MCP integrations for coding agents. It can be hosted by Overmind or self-hosted so traces and training data stay inside the user’s infrastructure. -
3
AgentScope
Build and run agents you can see, understand and trust
...AgentScope integrates seamlessly with tools, long-term memory systems, MCP, A2A (Agent-to-Agent) protocols, and observability frameworks. It also supports reinforcement learning workflows for tuning agents and improving performance across complex tasks. Deployable locally, serverless in the cloud, or on Kubernetes with OpenTelemetry support, AgentScope is built for both experimentation and production environments. -
4
Open Gauss
Project-scoped Lean workflow orchestrator from Math, Inc.
...One of its defining strengths is its optimization for multi-core and distributed environments, allowing it to efficiently process high volumes of concurrent transactions with minimal latency. OpenGauss also incorporates AI-based optimization techniques, such as intelligent query planning, performance prediction, and automated tuning, which help reduce operational complexity and improve efficiency. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
OpenManus
Open-source AI agent framework
OpenManus is an open-source AI agent framework designed to autonomously execute complex, multi-step tasks by combining reasoning, planning, and tool use. It enables developers to build agents that can think, act, and iterate toward goals rather than simply responding to prompts. The platform emphasizes task decomposition, allowing agents to break down objectives into smaller steps and execute them sequentially or recursively. OpenManus supports integration with external tools, APIs, and... -
6
rLLM
Democratizing Reinforcement Learning for LLMs
...With rLLM, developers can define custom “agents” and “environments,” and then train those agents via reinforcement learning workflows, possibly surpassing what vanilla fine-tuning or supervised learning might provide. The project is designed to support large-scale language models (including support for big models via integrated training backends), making it relevant for state-of-the-art research and production use. The framework includes tools for defining workflows, specifying objectives or reward functions, and managing training/policy updates across possibly distributed settings. -
7
Flint Chart
Visualization language that lets AI agents create expressive charts
Flint Chart is a visualization language and compiler built for AI-era chart creation. It lets agents and humans write compact, editable chart specifications without manually tuning every axis, label, scale, legend, or layout setting. The compiler uses data, semantic types, chart type, and encodings to derive polished chart settings automatically. One Flint input can compile into native Vega-Lite, ECharts, or Chart.js specifications. The repository includes a TypeScript library, an MCP server, a demo site, documentation, test data, and an early Python port. ... -
8
AI Agent Book
Deep Understanding AI Agents
...Ten chapters move from core concepts to context engineering, memory, RAG, knowledge graphs, MCP tools, and coding agents. Later material covers evaluation, supervised fine-tuning, reinforcement learning, self-improvement, multimodal interaction, robotics, and multi-agent cooperation. The repository includes 88 companion experiments, with more than 70 designed to run independently. Readers can access the source chapters, generated figures, code, and downloadable PDF or EPUB editions. Community translations provide versions in several languages alongside the original Chinese text. -
9
Ax
Build LLM powered Agents and "Agentic workflows"
Build intelligent agents quickly — inspired by the power of "Agentic workflows" and the Stanford DSPy paper. Seamlessly integrates with multiple LLMs and VectorDBs to build RAG pipelines or collaborative agents that can solve complex problems. Advanced features streaming validation, multi-modal DSPy, etc. We've renamed from "llmclient" to "ax" to highlight our focus on powering agentic workflows. We agree with many experts like "Andrew Ng" that agentic workflows are the key to unlocking the... -
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.
-
10
RecursiveMAS
Offical Implementation for "Recursive Multi-Agent Systems"
...The system uses a lightweight module called RecursiveLink to transfer and transform latent representations between agents, enabling seamless interaction even across heterogeneous models. It also incorporates an inner–outer loop training approach that optimizes the entire system collectively rather than tuning each agent separately. This design improves efficiency, reduces token usage, and stabilizes learning during iterative reasoning. -
11
AutoAgent AI
Autonomous harness engineering
AutoAgent is an experimental AI framework focused on autonomous agent engineering, where a meta-agent iteratively improves another agent’s architecture without direct human intervention. Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. ... -
12
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile. -
13
Mysti
AI coding dream team of agents for VS Code
...Instead of replacing the tools developers already use, it integrates with popular CLI-based coding assistants and routes work through a single, consistent UI inside the editor. The experience is organized around “personas” that change how the assistant approaches a task, such as architecture, debugging, security review, performance tuning, or refactoring, which helps structure the AI’s behavior for different goals. It also supports a brainstorm-style workflow where using more than one backend can produce competing solutions and then synthesize a best answer. Mysti is designed for speed and convenience with quick actions, toolbar persona switching, and a saved conversation history so work is not lost between sessions. -
14
Agent Lightning
The absolute trainer to light up AI agents
Agent Lightning is an open-source framework developed by Microsoft to train and optimize AI agents using techniques like reinforcement learning (RL), supervised fine-tuning, and automatic prompt optimization, with minimal or zero changes to existing agent code. It’s designed to be compatible with a wide range of agent architectures and frameworks — from LangChain and OpenAI Agent SDKs to AutoGen and custom Python agents — making it broadly applicable across different agent tooling ecosystems. Agent-Lightning introduces a lightweight training pipeline that observes agents’ execution traces, converts them into structured data, and feeds them into training algorithms, enabling users to improve agent behaviors systematically. ... -
15
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
Agent Reinforcement Trainer, or ART is an open-source reinforcement learning framework tailored to training large language model agents through experience, making them more reliable and performant on multi-turn, multi-step tasks. Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals. The framework is designed to integrate easily with Python applications, abstracting much of the RL infrastructure so developers can train agents without deep RL expertise or heavy infrastructure overhead. ... -
16
NVIDIA NeMo Agent Toolkit
Library for efficiently connecting and optimizing teams of AI agents
NVIDIA NeMo Agent Toolkit is an open-source framework designed to build, optimize, and manage AI agents across different development ecosystems. It provides enterprise-grade tools for improving agent performance, reliability, and observability throughout the development lifecycle. The toolkit integrates with popular agent frameworks such as LangChain, LlamaIndex, CrewAI, Microsoft Semantic Kernel, and Google ADK. Developers can monitor agent execution, trace workflows, and analyze... -
17
SuperAGI
A dev-first open source autonomous AI agent framework
An open-source autonomous AI framework to enable you to develop and deploy useful autonomous agents quickly & reliably. Join a community of developers constantly contributing to make SuperAGI better. Access your agents through a graphical user interface. Interact with agents by giving them input, permissions, etc. Agents typically learn and improve their performance over time with feedback loops. Run multiple agents simultaneously to improve efficiency and productivity. Connect to multiple...
- Previous
- You're on page 1
- Next
