Search Results for "context"
Sort By:
Showing 47 open source projects for "context"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
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.
-
1
Rust Docs MCP Server
Prevents outdated Rust code suggestions from AI assistants
The Rust Docs MCP Server fetches documentation for specified Rust crates, generates embeddings for the content, and provides an MCP tool to answer questions about the crate based on the documentation context. -
2
Crabtalk
Agents daemon that hides nothing
...It is implemented in Rust and focuses on delivering high performance, reliability, and low overhead compared to more complex agent frameworks. The system is built around a small set of core primitives, including skills, memory, context isolation, and extensions, which together enable flexible and modular agent behavior. CrabTalk emphasizes simplicity by avoiding unnecessary abstractions, allowing developers to maintain full control over how agents operate and interact with their environment. One of its key design goals is to address common issues in multi-agent systems, such as context fragmentation and coordination inefficiencies, by providing clearer structure and tighter control over execution. -
3
rtk
CLI proxy that reduces LLM token consumption
...When AI assistants execute shell commands during software development tasks, the resulting terminal output often contains large amounts of repetitive or irrelevant information that can overwhelm the model’s context window. RTK intercepts these command outputs and compresses them into concise summaries before sending them to the language model. This process helps maintain important information while removing redundant data such as boilerplate logs, long directory listings, or repetitive test outputs. By minimizing the amount of noise sent to the AI model, the tool improves reasoning quality and allows longer development sessions within the same context window. ... -
4
Macro
Macro is a unified interface for email, messages, tasks, calls, agents
...It is especially useful for teams that want their communication, operations, engineering work, and AI agents to share the same context layer. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
Kubie
A more powerful alternative to kubectx and kubens
kubie is an alternative to kubectx, kubens, and the k on prompt modification script. It offers context switching, namespace switching, and prompt modification in a way that makes each shell independent from others. It also has support for split configuration files, meaning it can load Kubernetes contexts from multiple files. You can configure the paths where Kubie will look for contexts, see the settings section. Kubie also has other nice features such as kubie exec which allows you to execute commands in a context and a namespace without having to spawn a shell and kubie lint which scans your k8s config files for issues and informs you of what they are. -
6
abtop
Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI
...It gives users a real-time view of active Claude Code, Codex CLI, and OpenCode sessions from local process and file state. The dashboard helps developers track token usage, context window percentage, rate limits, child processes, open ports, and multiple active profiles. It is read-only, so it does not require API keys or authentication and does not control the agents it observes. abtop is especially useful for developers running several agents across projects who need quick visibility into cost, quota pressure, context growth, and orphaned processes. ... -
7
glutin
A low-level library for OpenGL context creation
Glutin is a low-level library written in Rust that provides an interface for creating OpenGL contexts and handling windowing, events, and input. It serves as a foundational component for developing cross-platform graphical applications in Rust, offering developers the flexibility to build upon its abstractions for custom rendering solutions. -
8
best-claude-hud
Minimal Claude Code statusline HUD powered by Rust
...A terminal interface supports configuration, built-in themes, custom themes, model aliases, and custom context limits. The project supports major macOS, Linux, and Windows desktop architectures and avoids unnecessary Git locking while collecting repository status. -
9
yek
Serialize repositories into LLM-ready context w/ smart prioritization
...It scans projects using .gitignore rules to exclude irrelevant files and automatically filters out binary or oversized content. Yek prioritizes files based on Git history, placing more important content later in the output to align with how language models process context. Yek supports multiple directories, individual files, and glob patterns, making it flexible for different workflows. It can stream output when piped or save results to a temporary file, depending on usage. Configuration is handled through a yek.yaml file, allowing users to define ignore rules and priority settings. By consolidating code and documents into a single, ordered format, Yek simplifies preparing repositories for AI-driven analysis, debugging, or automation tasks. -
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.
-
10
TarpC
An RPC framework for Rust with a focus on ease of use
...The framework is transport-agnostic: it commonly uses Tokio with serde-based codecs, but you can plug in your own framing and serialization. It bakes in RPC concerns such as deadlines, cancellation, and context propagation so production behavior is predictable under load. The programming model feels native—call methods on a client stub and await results—while the server side exposes clean concurrency primitives for handling many requests. Because the interface is just Rust code, refactoring and IDE tooling work naturally without an external IDL. -
11
websocat
Command-line client for WebSockets, like netcat (or curl)
Netcat, curl and socat for WebSockets. Command-line client for WebSockets, like netcat (or curl) for ws:// with advanced socat-like functions. Connecting to and serving WebSockets from the command line. Executing external program and making it communicate to WebSocket using stdin/stdout. Text and binary modes, converting between lines (or null-terminated records) and messages. Inetd mode, UNIX sockets (including abstract namespaced on Linux). Integration with Nginx using TCP or UNIX sockets.... -
12
mirrord
Connect your local process and your cloud environment
mirrord lets developers run local processes in the context of their Kubernetes environment. It’s meant to provide the benefits of running your service on a cloud environment (e.g. staging) without actually going through the hassle of deploying it there, and without disrupting the environment by deploying untested code. It comes as a Visual Studio Code extension, an IntelliJ plugin, and a CLI tool. -
13
Anyhow
Flexible concrete Error type built on std::error::Error
...Its primary goal is to make error handling in applications easy: instead of defining lots of custom error types, you can use anyhow::Error (or the alias anyhow::Result<T>) for fallible functions. The crate supports attaching context to errors, so you can convert a low-level error (like “file not found”) into one with richer diagnostics (“Failed to read instructions from path X”) using .context() or .with_context(). It supports downcasting (so you can inspect the underlying error type), and for recent versions of Rust, it will capture backtraces by default when the underlying error type doesn’t already. ... -
14
HumanLayer
Open source IDE for orchestrating AI coding agents in large codebases
...HumanLayer integrates with modern AI models and coding assistants to automate tasks such as code research, planning, and implementation while maintaining a structured development process. HumanLayer introduces advanced context management techniques that help AI agents understand large repositories and operate effectively across multiple tasks. It also supports collaborative workflows where developers and AI agents can work together with human oversight and control. -
15
Destructive Command Guard
The Destructive Command Guard (dcg) is for blocking dangerous git
...It intercepts shell commands before execution and blocks operations that could erase files, rewrite Git history, destroy infrastructure, or remove data. The Rust implementation uses fast filtering and context-aware rules to distinguish dangerous execution from harmless text matches. Its modular security packs cover Git, filesystems, databases, containers, cloud platforms, Kubernetes, Terraform, and other tools. Users can inspect denials, enable agent-specific profiles, add allowlist entries, or temporarily bypass a rule when necessary. ... -
16
Casey just
Just a command runner
just is a handy way to save and run project-specific commands. -
17
Rust Port
The Rust workspace under rust/ is the current systems-language port
...It is often used as a sandbox for exploring how large-scale coding agents behave, including their decision-making processes, tool usage, and workflow orchestration. The system likely includes abstractions for handling file systems, executing commands, and maintaining context across sessions, allowing for more persistent and intelligent coding interactions. -
18
Seelen UI
The Fully Customizable Desktop Environment for Windows 10/11
...The project integrates additional desktop modules that can surface useful controls directly in the UI, such as media controls compatible with common players, reducing context switching. -
19
Code2Prompt
Convert codebases into structured prompts optimized for LLM analysis
...It analyzes a project directory, gathers relevant source files, and formats them into a single prompt that includes the source tree and code content. This approach helps developers quickly provide full project context to AI models without manually copying files or assembling prompts. code2prompt is built in Rust and focuses on performance, enabling fast traversal of large repositories while maintaining low resource usage. It also respects common project conventions such as .gitignore, ensuring that unnecessary files are automatically excluded from the generated prompt. ... -
20
Coral
One SQL interface over APIs, files, and live sources
...The project gives developers a command-line workflow for querying data, inspecting schemas, and working with tables. It is especially useful for agentic systems that need reliable access to context from multiple sources while keeping the runtime close to the developer’s environment. Coral focuses on composability, so different data sources can be treated as part of a shared query layer. Its main value is giving AI workflows a practical database-like abstraction over messy external information. -
21
aaif-goose
An open source, extensible AI agent that goes beyond code suggestions
...The project provides a desktop app, command-line interface, and API, which gives users multiple ways to work with the agent. goose is designed to connect with tools and local context so it can help complete practical tasks instead of only answering chat prompts. It is useful for developers, analysts, writers, and technical users who want an extensible assistant that can operate inside their environment. Its main value is bringing a native, flexible, and open agent workflow to everyday computer-based work. -
22
OpenHuman
Your Personal AI super intelligence. Private, simple and powerful
OpenHuman is an open-source personal AI assistant built to operate as a daily-life agent rather than a simple chatbot. It focuses on a private, desktop-first experience with a friendly interface, onboarding flows, and a persistent assistant that can remember context over time. The project connects to common productivity tools, gathers fresh information from integrations, and organizes user knowledge into a local memory system. It also includes practical agent tools such as web search, web fetching, file access, coding utilities, voice input, text-to-speech, and model routing. Its goal is to make an AI assistant feel continuously useful across meetings, messages, documents, tasks, and personal workflows. ... -
23
VT Code
VT Code - semantic AI coding agent
...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. It is highly configurable, allowing developers to define behavior, prompts, and workflows tailored to their projects. The tool is especially useful for developers who prefer lightweight, local-first environments but still want advanced AI assistance comparable to modern IDE-based tools. -
24
Amazon Q Developer CLI
Chat experience in your terminal
Amazon Q Developer CLI brings an agentic, chat-driven coding assistant to your terminal so you can ask for help, generate code, and perform routine dev tasks with natural language. It blends knowledge of your local workspace with command-line context to suggest commands, explain flags, and scaffold files or workflows. The tool aims to shorten the gap between intent and action by letting you request operations like creating a test, refactoring a function, or drafting a Dockerfile without leaving the shell. It also integrates with common developer flows, offering autocompletion and step-by-step plans before running potentially destructive actions. ... -
25
Claw Code
AI agent harness for AI coding agents
...The project provides a Python-based foundation for experimenting with agent workflows, tool integration, and task execution pipelines. 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.
