Search Results for "reason"
Sort By:
Showing 339 open source projects for "reason"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
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.
-
1
query-json
Faster, simpler and more portable implementation of `jq` in Reason
query-json is a faster, simpler, and more portable implementation of the jq language in Reason distributed as a dependency-free binary thanks to the OCaml compiler, and distributed to the web with js_of_ocaml. query-json allows you to write small programs to operate on top of json files with a concise syntax. Learn how to write a Programming Language with the OCaml stack using menhir and select with great error messages. -
2
RIBs
Uber's cross-platform mobile architecture framework
...Build cross-platform apps that have similar architecture, enabling iOS and Android teams to cross-review business logic code. Testability and Isolation. Classes must be easy to unit test and reason about in isolation. Individual RIB classes have distinct responsibilities like routing, business, view logic, creation. Plus, most RIB logic is decoupled from child RIB logic. This makes RIB classes easy to test and reason about independently. Tooling for developer productivity. RIBs come with IDE tooling around code generation, memory leak detection, static analysis and runtime integrations. -
3
remotefs
A client library to work with all file transfer protocols
...This is achieved through a trait called RemoteFs which exposes methods to operate on the remote file system. Currently, the library exposes a client for Sftp, Scp, Ftp and Aws-s3 as external libraries. You might be wondering, "why remotefs?" The first and foremost reason is to provide a generic interface over multiple protocols. For example, in termscp it allows the support of multiple protocols without any protocol-specific code. The second reason is that often, users just want a simple way to operate on a remote file system, however, they don't have the time to spend researching the ins and outs of each protocol. -
4
Guzzle Promises
A library for PHP with synchronous support
...A promise represents the eventual result of an asynchronous operation. The primary way of interacting with a promise is through its then method, which registers callbacks to receive either a promise's eventual value or the reason why the promise cannot be fulfilled. Callbacks are registered with the then method by providing an optional $onFulfilled followed by an optional $onRejected function. Resolving a promise means that you either fulfill a promise with a value or reject a promise with a reason. Resolving a promises triggers callbacks registered with the promises's then method. ... -
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
5
Bootstrap
HTML, CSS and JS framework for developing responsive websites and apps
Bootstrap is an HTML, CSS, and JS framework designed for developing responsive, mobile first projects on the web. It's one of the most popular front-end frameworks and for good reason: it simply makes web development faster and easier. People of all skill levels can create projects of all sizes with Bootstrap, and for all types of devices too. With Bootstrap, you get a host of nifty features such as precompiled CSS, impressive scalability, dozens of custom HTML and CSS components and more. -
6
Loki Mode
Multi-agent autonomous startup system for Claude Code
...By supporting multiple AI providers (like Claude Code, OpenAI Codex CLI, and Google Gemini CLI), loki-mode dynamically selects and spawns only the needed agents for a given project, optimizing computational resources and task throughput. Its Reason-Act-Reflect-Verify (RARV) cycle with self-verification loops emphasizes quality and resilience, automating end-to-end development lifecycles. -
7
Coconut
Training Large Language Model to Reason in a Continuous Latent Space
Coconut is the official PyTorch implementation of the research paper “Training Large Language Models to Reason in a Continuous Latent Space.” The framework introduces a novel method for enhancing large language models (LLMs) with continuous latent reasoning steps, enabling them to generate and refine reasoning chains within a learned latent space rather than relying solely on discrete symbolic reasoning. It supports training across multiple reasoning paradigms—including standard Chain-of-Thought (CoT), no-thought, and hybrid configurations—using configurable training stages and latent representations. ... -
8
emuiibo
Virtual amiibo (amiibo emulation) system for Nintendo Switch
...A virtual amiibo is detected by emuiibo based on two aspects: a amiibo.json and a amiibo.flag file must exist inside the virtual amiibo's folder mentioned above. If (for whatever reason) you would like to disable a virtual amiibo from being recognised by emuiibo, just remove the flag file, and create it again to enable it. While old emuiibo formats are supported and converted to the current format (see above), it is strongly suggested to, unless bin dumps might be indispensable, emuiigen be used, our PC utility designed to create and edit virtual amiibos. -
9
LongBench
LongBench v2 and LongBench (ACL 25'&24')
LongBench is a comprehensive benchmark designed to evaluate the ability of large language models to understand and reason over very long textual contexts. Traditional language model benchmarks typically evaluate tasks involving relatively short inputs, which does not reflect many real-world applications such as analyzing large documents or entire code repositories. LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. ... -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
10
ReCall
Learning to Reason with Search for LLMs via Reinforcement Learning
ReCall is an open-source framework designed to train and evaluate language models that can reason through complex problems by interacting with external tools. The project builds on earlier work focused on teaching models how to search for information during reasoning tasks and extends that idea to a broader system where models can call a variety of external tools such as APIs, databases, or computation engines. Instead of relying purely on static knowledge stored inside the model, ReCall allows the language model to dynamically decide when it should retrieve information or invoke external capabilities during the reasoning process. ... -
11
StabilityMatrix
Multi-Platform Package Manager for Stable Diffusion
StabilityMatrix is a project that helps organize, evaluate, and compare generative AI models and their behavior across prompts, datasets, or configuration settings. It provides a framework to run experiments systematically—capturing inputs, model configurations, outputs, and metrics—so researchers and practitioners can reason about differences in quality, robustness, and failure modes. The repository often bundles tooling for automated prompt sweeping, scoring heuristics (such as diversity, coherence, or task-specific metrics), and visualization helpers to make comparisons interpretable. This approach is useful for model selection, prompt engineering, and benchmarking new checkpoints against baseline models under reproducible conditions. ... -
12
Insomnia API Client
The open-source, cross-platform API client for GraphQL
Insomnia is an open-source, cross-platform API client for GraphQL, REST, and gRPC. Deliver high-quality APIs through standards and collaboration with the Insomnia API design platform. There is a reason developers love Insomnia. With our streamlined API client, you can quickly and easily send REST, SOAP, GraphQL, and GRPC requests directly within Insomnia. Accelerate your teams through spec-driven design-first API development. Catch issues earlier, centralize standards, and adopt an API workflow that works with your existing tools. ... -
13
Fido
A PowerShell script to download Windows or UEFI Shell ISOs
...This script exists because, while Microsoft does make retail ISO download links freely and publicly available (at least for Windows 8 through Windows 11), up until recent releases, most of these links were only available after forcing users to jump through a lot of unwarranted hoops that created an exceedingly counterproductive, if not downright unfriendly, consumer experience, that greatly detracted from what people really want (direct access to ISO downloads). As to the reason one might want to download Windows retail ISOs, as opposed to the ISOs that are generated by Microsoft's own Media Creation Tool (MCT). -
14
SuperPrompt
Experimental prompt framework exploring reasoning structures in AI
SuperPrompt is an experimental open source project focused on designing complex prompts intended to help researchers and developers better understand how AI agents reason and respond. It explores structured prompt engineering techniques that combine symbolic expressions, logical constructs, and conceptual frameworks to guide large language models toward deeper reasoning processes. Its main concept revolves around a highly structured prompt format that includes tagged sections for reasoning, analysis, conceptual expansion, and recursive thinking patterns. ... -
15
Qwen3.5
Qwen3.5 is the large language model series developed by Qwen team
Qwen3.5 is part of Alibaba’s Qwen family of large language and multimodal foundation models, designed to power advanced AI applications such as chatbots, coding assistants, and autonomous agents. The project represents a significant step toward “agentic AI,” meaning models that can reason through multi-step tasks and interact with external tools or environments rather than only generating text. Qwen3.5 builds on earlier Qwen generations by improving multilingual understanding, reasoning ability, and efficiency, while also introducing native multimodal capabilities that allow the model to work with both language and visual inputs. ... -
16
Jinja
Ultra fast and expressive template engine
...It offers full unicode support, a sandboxed environment for safe executions, and so much more. Jinja is among the most widely used template engines for Python, and for good reason. It is both beautiful and powerful, and makes a template designer’s job a lot easier. Jinja is inspired by Django's templating system, but steps it up with an expressive language that results in more powerful tools, plus an automatic HTML escaping system for utmost security. Internally Jinja is based on Unicode and will run on a wide range of Python versions. -
17
LeetCode Book
Comprehensive study guide for coding interviews
...It organizes problems by topic—arrays, linked lists, stacks/queues, trees/graphs, dynamic programming, greedy, backtracking, and math—so you can study systematically. Explanations are concise but intentional, highlighting why a pattern fits, how to reason about boundary cases, and the time/space trade-offs. Many entries include template code and “swap-in” variations, helping you recognize how the same technique adapts across similar problems. The book also emphasizes problem-solving habits like deriving invariants, choosing appropriate data structures, and verifying with small counterexamples. ... -
18
Keycastr
KeyCastr, an open-source keystroke visualizer
...On newer versions of macOS (10.15+) there is a new Input Monitoring menu under Security & Privacy within the System Preferences app, and KeyCastr will appear there automatically the first time you run it. Simply unlock this menu and check the box next to KeyCastr to enable it. On older versions of macOS, or if for some reason the app doesn't appear under the Input Monitoring menu (or if you want to pre-enable it) then you may manually add it to the list of apps in the Accessibility menu. If KeyCastr is already in the list, then click the, button and add KeyCastr again to be certain that the right application is chosen. Make sure to check the "Display all keystrokes" checkbox if you would like to display more than just the modifier keys. -
19
EnvFile
EnvFile 3.x is a plugin for JetBrains IDEs
...Luckily, it was possible to make few assumptions about IDEA's internal implementation and make it work. Such integration is very fragile and it's not immediately clear if it will affect any existing integrations and when it will break. For that reason there is a special option to Enable Experimental Integrations that can be enabled when desired and should prevent other integrations from breaking. -
20
DeepSeek Engineer v2
A powerful coding assistant application
...It includes safeguards such as path validation, directory traversal protection, file size limits, and binary file exclusion. Overall, it is designed for developers who want a conversational coding tool that can inspect, modify, and reason about project files from the command line. -
21
Radarr
A fork of Sonarr to work with movies à la Couchpotato
Radarr makes failed downloads a thing of the past. Password-protected releases, missing repair blocks or virtually any other reason? no worries. Radarr will automatically blacklist the release and tries another one until it finds one that works. Ensure you get the right release every time! Custom Formats allow fine control over release prioritization and selection. As simple as a single preferred word or as complex as you want with multiple criteria and regex. -
22
Lemon AI
Full-stack Open-source Self-Evolving General AI Agent
...It integrates with local large language models through tools such as Ollama, vLLM, and other model runtimes while also allowing optional connections to external cloud models. The system includes a multi-agent architecture that supports planning, action execution, reflection, and memory, allowing the agent to reason through tasks and refine results iteratively. A key component of the framework is a virtual machine sandbox environment that safely executes code generated by the agent without affecting the host system. -
23
Franz 5
Franz is a free messaging app for services like WhatsApp, Slack, etc,
...This makes Franz the perfect tool to manage multiple business and private accounts all at the same time. You could even use five different Facebook Messenger accounts at once, if some inexplicable reason urges you to do so. Franz Workspaces help you create distraction-free work environments by making sure you’re only getting the notifications you absolutely need while working on a specific project. Setting up different Workspaces for business and private life is also an easy way to disconnect from work at home. -
24
Claude BugHunter
A Claude Code skill bundle for bug hunting
Claude-BugHunter is a Claude Code skill bundle focused on bug hunting, security testing, and external red-team research workflows. It packages a large collection of specialized skills, slash commands, and disclosed-report patterns so Claude Code can reason through common vulnerability classes more systematically. The project is meant to help authorized testers structure reconnaissance, triage, hypothesis building, exploitation reasoning, and reporting. It includes curated patterns from public vulnerability reports, making it useful as a learning and workflow reference. Because it supports security testing, it should only be used on systems where the user has permission to test. ... -
25
Open-AutoGLM
An open phone agent model & framework
Open-AutoGLM is an open-source framework and model designed to empower autonomous mobile intelligent assistants by enabling AI agents to understand and interact with phone screens in a multimodal manner, blending vision and language capability to control real devices. It aims to create an “AI phone agent” that can perceive on-screen content, reason about user goals, and execute sequences of taps, swipes, and text input via automated device control interfaces like ADB, enabling hands-off completion of multi-step tasks such as navigating apps, filling forms, and more. Unlike traditional automation scripts that depend on brittle heuristics, Open-AutoGLM uses pretrained large language and vision-language models to interpret visual context and natural language instructions, giving the agent robust adaptability across apps and interfaces.
