Search Results for "performance"
Sort By:
Showing 35 open source projects for "performance"
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.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
codebase-memory-mcp
High-performance code intelligence MCP server
codebase-memory-mcp is a high-performance code intelligence MCP server built for AI coding agents. It indexes codebases into a persistent knowledge graph so agents can understand architecture, symbols, call chains, routes, and cross-service relationships without reading every file repeatedly. The project uses tree-sitter AST analysis across 158 languages and adds Hybrid LSP type resolution for major languages like Python, TypeScript, JavaScript, Go, C#, Java, Rust, C, and C++. ... -
2
Claw Code
AI agent harness for AI coding agents
...It emphasizes harness engineering—how agents are structured, how they interact with tools, and how they maintain context during execution. The system is being actively expanded, with a Rust-based runtime in development to improve performance and memory safety. Overall, Claw Code serves as a research-driven platform for advancing agent-based software development systems. -
3
darwin-skill
Autoresearch-inspired autonomous skill optimization for Claude Code
darwin-skill is an experimental framework designed to automatically improve AI agent “skills” through iterative evaluation and optimization loops inspired by machine learning training processes. Instead of treating prompts or skill definitions as static assets, the system applies a continuous improvement cycle that evaluates performance, proposes changes, tests outcomes, and either retains or reverts modifications. The framework introduces a scoring system across multiple dimensions, enabling quantitative assessment of skill quality and ensuring that only improvements are preserved over time. It incorporates a “ratchet mechanism” similar to version control workflows, guaranteeing that performance never degrades as iterations progress. ... -
4
Zed
High-performance, multiplayer code editor from the creators of Atom
Zed is a next-generation code editor designed for high-performance collaboration with humans and AI. Written from scratch in Rust to efficiently leverage multiple CPU cores and your GPU. Integrate upcoming LLMs into your workflow to generate, transform, and analyze code. Chat with teammates, write notes together, and share your screen and project. Multibuffers compose excerpts from across the codebase in one editable surface. -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
Paseo
Orchestrate coding agents remotely from your phone, desktop and CLI
Paseo is a modern development platform designed to streamline the creation and management of web applications through a focus on simplicity, performance, and developer experience. It provides a structured environment for building applications with minimal configuration, allowing developers to focus on core functionality rather than setup complexity. The platform likely includes tools for routing, state management, and component organization, enabling rapid development of scalable applications. ... -
6
Kodus
AI code reviews, just like your senior dev would do
...The platform often includes model management, scalable training workflows, and orchestration patterns that help teams move from research or prototypes to production-ready AI deployments. Through configurable pipelines and a focus on modularity, it supports experimentation while maintaining reproducibility and performance. Its tooling is typically designed to handle real-world imperatives like logging, monitoring, versioning, and hooking into operational infrastructure. -
7
MiniMax-M2.1
MiniMax M2.1, a SOTA model for real-world dev & agents.
MiniMax-M2.1 is an open-source, state-of-the-art agentic language model released to democratize high-performance AI capabilities. It goes beyond a simple parameter upgrade, delivering major gains in coding, tool use, instruction following, and long-horizon planning. The model is designed to be transparent, controllable, and accessible, enabling developers to build autonomous systems without relying on closed platforms. MiniMax-M2.1 excels in real-world software engineering tasks, including multilingual development and complex workflow automation. ... -
8
Taipy
Turns Data and AI algorithms into production-ready web applications
From simple pilots to production-ready web applications in no time. No more compromise on performance, customization, and scalability. Taipy enhances performance with caching control of graphical events, optimizing rendering by selectively updating graphical components only upon interaction. Effortlessly manage massive datasets with Taipy's built-in decimator for charts, intelligently reducing the number of data points to save time and memory without losing the essence of your data's shape. ... -
9
.NET Agent Skills
Repository for skills to assist AI coding agents with .NET and C#
.NET Agent Skills is Microsoft’s curated skill repository for helping AI coding agents work more accurately with .NET and C# projects. It provides structured knowledge packs and custom agents that guide coding assistants through common development, debugging, migration, build, package, and performance tasks. The repository covers core .NET work as well as more specialized areas such as Entity Framework, MSBuild, NuGet, .NET upgrades, .NET MAUI, and AI-related .NET development. Its purpose is to reduce trial and error by giving agents task-specific context and repeatable workflows. The project also includes evaluation and dashboard support to track skill performance over time. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...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. -
11
Codeflash
Optimize your code automatically with AI
...Automate optimizing all future code you will write by installing Codeflash as a GitHub action. Optimize a Python workflow python myscript.py end-to-end by running codeflash optimize myscript.py. Optimizing the performance of new code for a Pull Request through GitHub Actions. This lets you ship code quickly while ensuring it remains performant. -
12
Oh My OpenCode Slim
Slimmed, cleaned and fine-tuned oh-my-opencode fork
...It supports multiple AI providers and models, enabling users to mix and match capabilities depending on cost, speed, and performance requirements. -
13
Gemma Chat
Local AI chat + coding agent for Apple Silicon, powered by Gemma 4
...It emphasizes privacy and independence by avoiding cloud dependencies, allowing all interactions and data to remain local. The system integrates model selection and execution directly into the app, giving users control over performance and behavior. It is particularly aligned with the “vibe coding” approach, where users iteratively build and modify projects through conversational prompts. Overall, gemma-chat provides a streamlined, developer-focused environment for local AI experimentation and productivity. -
14
Qwen3-Coder
Qwen3-Coder is the code version of Qwen3
...Its flagship version, Qwen3-Coder-480B-A35B-Instruct, features a massive 480 billion-parameter Mixture-of-Experts architecture with 35 billion active parameters, delivering top-tier performance on coding and agentic tasks. This model sets new state-of-the-art benchmarks among open models for agentic coding, browser-use, and tool-use, matching performance comparable to leading models like Claude Sonnet. Qwen3-Coder supports an exceptionally long context window of 256,000 tokens, extendable to 1 million tokens using Yarn, enabling repository-scale code understanding and generation. ... -
15
AsmJit
Low-latency machine code generation
AsmJit is a low-level code generation library designed for dynamically creating machine code at runtime, enabling just-in-time (JIT) compilation for performance-critical applications. It provides a high-level API that abstracts away the complexity of writing raw assembly while still allowing fine-grained control over instruction generation. The library supports multiple architectures, including x86 and x64, making it versatile for cross-platform development. It is commonly used in applications such as emulators, compilers, and high-performance computing systems where runtime optimization is essential. asmjit emphasizes low latency and efficiency, ensuring that generated code executes quickly without significant overhead. ... -
16
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it
...GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI). -
17
Context Mode
Context window optimization for AI coding agents
...It is particularly useful for large codebases, where naive context inclusion can lead to inefficiency or irrelevant outputs. The system encourages modular and selective context injection, improving both performance and cost efficiency. It also aligns with emerging patterns in AI-assisted development, where context orchestration becomes a critical component of productivity. Overall, context-mode represents a shift toward more intentional and structured interaction between developers and AI systems. -
18
VT Code
VT Code - semantic AI coding agent
VTCode is a terminal-based AI coding agent designed to provide semantic code understanding and interactive assistance directly within a command-line environment. It is implemented in Rust and focuses on performance, portability, and deep integration with developer workflows that rely on terminal tools. The system leverages syntax-aware parsing technologies such as tree-sitter and AST-based analysis to understand code structure rather than relying solely on raw text, which enables more accurate and context-aware suggestions. VTCode operates as an agent rather than a simple autocomplete tool, meaning it can interpret user intent, navigate codebases, and assist with multi-step tasks. ... -
19
Pi Agent
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI
...The framework is built around extensibility, allowing developers to create custom tools, workflows, and autonomous coding experiences. Pi also encourages the sharing of real-world AI coding sessions to improve agent performance through practical usage data instead of synthetic benchmarks. With its modular architecture, active open-source community, and support for advanced agent capabilities, Pi provides a comprehensive foundation for building next-generation AI development tools and autonomous c -
20
MiniMax-M2
MiniMax-M2, a model built for Max coding & agentic workflows
MiniMax-M2 is an open-weight large language model designed specifically for high-end coding and agentic workflows while staying compact and efficient. It uses a Mixture-of-Experts (MoE) architecture with 230 billion total parameters but only 10 billion activated per token, giving it the behavior of a very large model at a fraction of the runtime cost. The model is tuned for end-to-end developer flows such as multi-file edits, compile–run–fix loops, and test-validated repairs across real... -
21
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
...Developed with MindSpore and later made PyTorch-compatible, it is capable of multilingual code generation, cross-lingual code translation, code completion, summarization, and explanation. It has been benchmarked on HumanEval-X, a multilingual program synthesis benchmark introduced alongside the model, and achieves state-of-the-art performance compared to other open models like InCoder and CodeGen. CodeGeeX also powers IDE plugins for VS Code and JetBrains, offering features like code completion, translation, debugging, and annotation. The model supports Ascend 910 and NVIDIA GPUs, with optimizations like quantization and FasterTransformer acceleration for faster inference. -
22
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. Designed to reason efficiently and decompose tasks like an experienced architect, M2.5 plans features, structure, and system design before generating code. The model supports full-stack development across web, mobile, and desktop platforms, covering the entire lifecycle from system design to testing and code review. ... -
23
Edgee
AI gateway with token compression for Claude Code, Codex, and more
...It integrates AI capabilities into edge environments, making it possible to perform inference, personalization, and decision-making at the point of interaction. Edgee is optimized for performance and scalability, leveraging distributed execution to handle high volumes of requests efficiently. It also emphasizes developer experience, providing tools and abstractions that simplify deployment and orchestration across edge nodes. -
24
Mods
AI on the command line
...The project is useful for summarizing logs, rewriting text, formatting data, generating Markdown, producing JSON, and analyzing command output without leaving the shell. It works well with local LLMs and hosted providers, which gives users flexibility depending on privacy, cost, and performance needs. Mods fits naturally into Unix-style workflows because it can read from standard input and produce output that other commands can continue processing. Its main value is bringing practical AI assistance into everyday terminal automation. -
25
SmallCode
AI coding agent optimized for small LLMs. 87% benchmark
SmallCode is a terminal-native AI coding agent optimized for local models running on consumer hardware. It is designed to extract useful coding performance from smaller LLMs, especially models in the 7B to 20B range. The project focuses on making local coding assistance practical without requiring massive cloud-hosted models for every task. Its workflow is built around terminal usage, which makes it suitable for developers who prefer command-line control and local project context. smallcode emphasizes efficient agent behavior, careful tool use, and benchmark-driven improvements for constrained models. ...
