Search Results for "context" - Page 33
Sort By:
Showing 2139 open source projects for "context"
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.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry 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
MCP Agent Mail
Asynchronous coordination layer for AI coding agents
...It gives each agent a persistent identity, inbox, outbox, searchable history, and threaded Markdown conversations. Agents can send decisions, status updates, images, and attachments without relying on a human to relay context between parallel sessions. Advisory file reservations let an agent declare intended edits to files or patterns, reducing accidental overlap without enforcing rigid locks. Git stores human-auditable communication artifacts, while SQLite supports indexing, search, and operational queries. The HTTP-only FastMCP server works with clients such as Claude Code, Codex, Gemini CLI, and other MCP-compatible tools. ... -
2
code-review-graph
Local-first code intelligence graph for MCP and CLI
...It parses source files with Tree-sitter and stores functions, classes, imports, calls, inheritance, and test relationships in a SQLite graph. When code changes, blast-radius analysis identifies the callers, dependents, and tests most likely to be affected. AI coding assistants can query this focused context through MCP instead of repeatedly scanning an entire codebase. Incremental indexing reparses only changed files and their relevant dependencies, making it practical for large repositories and monorepos. The command-line installer can detect and configure numerous supported coding tools automatically. It also offers watch mode, hooks, skills, a VS Code extension, and review-oriented risk analysis. -
3
TabFM
scikit-learn compatible tabular foundation model
...It is designed to work with mixed numerical and categorical columns without requiring a custom training run for every new table. Instead of fitting model weights to the user’s dataset, TabFM uses in-context learning by reading training examples and test rows together at inference time. The library provides scikit-learn-compatible classifier and regressor interfaces, which makes it familiar for data scientists already using Python ML workflows. It supports both JAX and PyTorch backends and can automatically download pretrained TabFM v1.0.0 weights. ... -
4
plakar
plakar is a backup solution powered by Kloset and ptar
plakar is an open-source backup solution designed to protect files, application data, and contextual metadata in a scalable way. It goes beyond basic file copying by storing data and its surrounding context inside Kloset, an immutable open-source data store. The project focuses on making backups easy to start while still supporting advanced data protection scenarios. It emphasizes security through end-to-end encryption for both backup data and metadata. Plakar is also built for reliability, using immutable storage to reduce the risk of accidental modification or corruption. ... -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
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. -
6
SmallCode
AI coding agent optimized for small LLMs. 87% benchmark
...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. Its main value is giving developers a compact coding-agent environment that treats small local models as first-class tools. -
7
Swift Macros
A curated list of awesome Swift Macros
Swift Macros is a curated collection of Swift macro resources, tools, examples, and learning material. It is intended for developers who want to understand, build, test, and distribute Swift macros in modern Swift projects. The repository gathers community-created macros alongside frameworks, articles, Apple resources, tutorials, and related tooling. Its structure makes it easier to discover practical macro use cases without searching across scattered blog posts and packages. It is... -
8
RepoBar
Show status of GitHub Repos right in your menu bar and terminal
...Built with SwiftUI and AppKit, the tool surfaces key repository signals such as CI status, pull requests, issues, releases, traffic metrics, and recent activity directly in the system menu bar. RepoBar is designed for developers managing multiple repositories simultaneously, offering glanceable insights that reduce context switching and improve workflow awareness. The application also tracks local Git repository state, helping users correlate remote repository activity with their local development environment. It includes a bundled CLI and supports configurable refresh schedules, repository pinning, and fast navigation to GitHub actions or checks. ... -
9
AutoCrop-Vertical
Smart video converter using YOLOv8 and FFmpeg
...Instead of applying a static center crop, the system intelligently tracks people or key objects to preserve visual focus and composition. When cropping would degrade the scene, it can switch to alternative layouts such as letterboxing to maintain context. The tool integrates FFmpeg for encoding and rendering, ensuring efficient processing and compatibility with standard video workflows. It supports multiple output aspect ratios and quality settings, allowing customization for different platforms. Designed as a lightweight script, it runs locally and provides a cost-free alternative to commercial video reframing tools. -
Paessler - Monitor Your Whole Network in MinutesWaiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.
-
10
pompelmi
Minimal Node.js wrapper around ClamAV
...It is designed to support local or remote model backends, allowing users to choose between privacy-focused local execution or cloud-based services. Pompelmi also includes features for managing conversations, enabling users to maintain context and revisit previous interactions. Its lightweight architecture ensures that it can run efficiently without requiring significant resources. Overall, Pompelmi provides a straightforward entry point for users looking to interact with AI systems without dealing with complex configurations. -
11
BTC Trading Since 2020
Public BTC trading context since 2020
BTC-Trading-Since-2020 is a cryptocurrency trading analysis project that focuses on evaluating Bitcoin trading strategies using historical data and algorithmic approaches. The repository serves as both a research and experimentation environment, allowing users to explore how different strategies perform under varying market conditions. It includes backtesting capabilities that enable users to simulate trades over historical Bitcoin price data, helping to identify profitable patterns and risk... -
12
Markplane
AI-native, markdown-first project management
...The system is designed to integrate seamlessly with AI coding assistants by compressing project information into token-efficient summaries that models can understand and act on. It enables developers to manage their workflow entirely within their existing tools, avoiding context switching between code and project management platforms. The inclusion of an MCP server allows AI systems to query, update, and manage project data directly through natural language interactions. By leveraging version control, it ensures that all project decisions and changes are tracked alongside code. -
13
ComfyUI-HunyuanVideoWrapper
ComfyUI wrapper nodes for HunyuanVideo
...The system introduces specialized nodes such as text-image encoders that allow multiple image inputs to be referenced directly within prompts. This makes it possible to guide generation using both visual and textual context simultaneously. The wrapper is designed to fit seamlessly into ComfyUI pipelines, enabling chaining with other nodes for advanced workflows. It supports prompt-based referencing of images, where placeholders in text correspond to connected inputs, allowing fine control over generation behavior. The project is particularly useful for creators experimenting with multimodal AI video synthesis. -
14
claude-token-efficient
One CLAUDE.md file. Keeps Claude responses terse
...Instead of modifying model architecture or APIs, it uses a drop-in CLAUDE.md file that constrains how the model responds, enforcing concise output and eliminating unnecessary phrasing patterns. The approach focuses on removing redundant explanations, overly polite language, and repeated context, which are common contributors to excessive token consumption in AI-generated responses. It is particularly useful in high-volume or agent-based workflows where output tokens accumulate quickly and significantly impact cost and latency. The system works best in iterative or automation-heavy environments where consistent formatting and brevity are more valuable than exploratory reasoning. -
15
colleague-skill
Transform a cold separation into a warm Skill
colleague-skill is a specialized agent skill designed to simulate a collaborative teammate within AI-driven workflows, enabling agents to behave more like human colleagues in problem-solving scenarios. The project focuses on enhancing interaction quality by introducing role-based behavior, contextual awareness, and cooperative task execution. It allows agents to provide suggestions, feedback, and alternative approaches, mimicking real-world collaboration dynamics. The system likely... -
16
Claude Code Architecture Study
Research on Coding Agents
Claude Code Architecture Study is an educational and experimental repository designed to teach developers how to build, configure, and understand AI coding agents from first principles. The project focuses on breaking down the architecture of agentic systems, including how models perceive context, make decisions, and execute actions in a coding environment. It likely provides step-by-step examples, conceptual explanations, and practical implementations that guide users through creating their own agents. The framework emphasizes learning by doing, allowing users to experiment with agent behavior, prompt design, and workflow structuring. ... -
17
Minisign
A dead simple tool to sign files and verify digital signatures
...Users can generate key pairs, sign files, and verify signatures using straightforward commands, enabling secure validation of files across different environments. Minisign supports deterministic signatures and includes features such as trusted comments that allow embedding metadata within signatures for additional context and verification integrity. -
18
AgentScope Java
Agent-Oriented Programming for Building LLM Applications
...The framework includes runtime controls such as safe interruption and graceful cancellation to manage agent execution robustly in production environments. It also supports human-in-the-loop intervention, allowing developers or users to inject guidance at any point during reasoning while preserving state and tool context. Built with enterprise needs in mind, AgentScope Java integrates into traditional Java stacks and provides structured abstractions for memory, workflows, and tool invocation. -
19
Toaster Frame
Android toast frame, dedicated to treating various difficult problems
Toaster is a lightweight Android utility library that enhances and standardizes toast message behavior across different devices and OS versions. The project addresses inconsistencies in native Android toast implementations by providing a more reliable and customizable messaging experience. It focuses on ensuring that toast notifications display correctly even on heavily customized Android skins. The library is designed for easy integration, allowing developers to replace default toast usage... -
20
claude-code-best-practice
Practice made claude perfect
...The repository emphasizes modularity and progressive disclosure, encouraging developers to build reusable components that can be invoked on demand. It also explores operational concerns such as permissions management, sandboxing, debugging workflows, and context optimization. By combining conceptual guidance with concrete examples and configuration patterns, the project helps teams move from experimental AI usage toward more production-ready agent orchestration. -
21
GitNexus
Zero-Server Code Intelligence Engine
...The tool allows developers to drop in a GitHub repository or ZIP archive and automatically generate a relational map of files, dependencies, and structural relationships. Its core concept centers on precomputed relational intelligence, enabling AI systems to retrieve comprehensive context with minimal queries. GitNexus includes a built-in Graph RAG agent that helps users explore and understand complex repositories through intelligent navigation and querying. Because the system runs client-side, it emphasizes privacy and portability without requiring backend infrastructure. Overall, GitNexus is designed for developers, code reviewers, and AI tooling builders who need fast, visual codebase comprehension. -
22
VideoRAG
"VideoRAG: Chat with Your Videos
...This approach allows it to handle videos of arbitrary length without requiring the entire content to be passed into the model at once, overcoming token limits and enabling detailed, context-aware interaction. -
23
CodexMonitor
An app to monitor the (Codex) situation
...The interface complements direct interactions with the agents by integrating things like file trees, prompt libraries, reasoning logs, and CLI session panels, making it easier to manage long-running dialogues and context switches without leaving the app. In addition to conversation views, CodexMonitor includes tools for Git and GitHub integration—including diffs, logs, and pull request management—so code inspection and review workflows can be coordinated alongside agent interaction. -
24
Map of GitHub
Inspirational Mapping
Map-of-GitHub is an inventive project that visually represents the global distribution of GitHub users and repositories on a map of the world, revealing geographic patterns and community concentrations across countries and cities. The project processes GitHub account metadata and GPS or location information (when available) to plot users’ locations and draw connections between communities, resulting in an exploratory visualization where density and network effects become instantly visible.... -
25
Peta Core
Secure vault, managed runtime, audit trail, and policy-based approvals
Peta Core is an open-source project that aims to provide foundational infrastructure for building extensible, distributed applications and services, particularly in the context of agentic systems and modern tooling. It typically encompasses core abstractions, protocols, and utilities that other modules in the PETA ecosystem can build upon, offering patterns for service discovery, messaging, workflow orchestration, and plugin integration. PETA-Core may include frameworks for managing agent lifecycles, standard interfaces for connectors, and support for consistent configuration across components, making it easier to assemble complex, multi-part applications with clear boundaries and reusable logic. ...
