Directory
Published directory entries matching your search.
DeepSWE is a benchmarking platform that evaluates frontier coding agents on original, long-horizon software engineering tasks. It provides a public leaderboard, task examples, and tracks results across 113 tasks, 91 repositories, 5 programming languages, and 28 models.
DemoGPT is a tool that enables users to create agentic applications using prompts. It provides all components required for LLM agent development, including tools, prompts, frameworks, and models, in a single package.
Design Arena is a global crowdsourced benchmark for AI-generated design. It allows users to challenge, vote on, and crown winning design outputs, access category-specific leaderboards for assets including websites, slides, images, video, audio, and code, and use top AI models to generate a wide range of design and development assets. Millions of users across over 190 countries use the platform to discover and compare AI model capabilities.
Devin is an AI coding agent and software engineer that helps developers build better software faster. It runs in the cloud or on a machine, tests in its own browser, and works from problem to merged pull request. Plans include Free, Pro, Max, Teams, and Enterprise.
Devv is a native AI coding agent designed for indie builders and small teams to develop full-stack AI-powered products. It offers native integrations and eliminates the need for glue code to help users ship products quickly.
Dify is an open-source LLM app development platform with a visual canvas for AI workflows and RAG pipelines, plus model management and observability. It can be deployed on cloud, VPC, or self-hosted, and integrates with proprietary and open-source LLMs.
DigitalOcean describes an AI-native cloud platform with a unified stack for agents, inference and cloud infrastructure. Products listed include Managed Agents, Learning Services, Data Services, an Inference Engine with over 75 models, and core cloud services such as Droplets, Kubernetes and App Platform. Harness Runtime is listed starting at $0.0535/hr for durable cloud sandboxes for AI coding agents.
This is the documentation for Ellipsis, a platform that enables running internal agents in the cloud via Claude Code or Codex, with support for custom tools, secrets, and MCP servers. Users define agents as YAML configuration files in their repositories, and Ellipsis executes the agents to build features, fix bugs, and investigate production issues. The platform also includes integrations with GitHub, Slack, Linear, and Sentry, plus support for sessions, environments, secrets, permissions, and usage budgets.
Dorothy is a free and open source desktop app for orchestrating Claude Code, Codex, Gemini, Grok and local agents. It runs multiple agents simultaneously, each in an isolated PTY terminal session, and includes a Super Agent that delegates tasks to other agents via MCP tools, plus Kanban task management and scheduled tasks.
DrivenData hosts online machine learning competitions with social impact and works with mission-driven organizations on data science and engineering projects. It also maintains open-source projects for the data science community and shares prize-winning solutions from past competitions on GitHub. Areas of work include public health, conservation and international development.
An article presenting initial impressions of DSPy, a framework developed by the Stanford NLP group for algorithmically optimizing language model prompts. The author describes DSPy as closing the loop of prompt engineering by turning a manual process into a structured machine learning workflow. The piece notes it is not a substitute for the official documentation and covers topics such as teleprompter, optimization, compile, bootstrapping and metric functions.
E2B is an open-source, secure environment built with real-world tools for use with enterprise-grade AI agents. The project's GitHub repository includes documentation for installing the E2B SDK, obtaining an API key, and running sandboxed environments to execute commands. The repository accepts community contributions.
Early days of AI is a blog post by Elad Gil that discusses the early development of machine learning systems and the AI hype cycle. Gil argues that recent advances like transformers and diffusion models represent a new era, distinct from previous AI. He draws on his experience at Google, Twitter, and as an investor.
Machine learning development environment for data science and AI/ML engineering teams.
EspNet is an end-to-end speech processing toolkit hosted on GitHub. It is open-source software designed for speech processing tasks, with repository documentation covering installation steps, quick start guidance, and details of supported processing tasks. Contributors can participate in its development via the GitHub platform.
Open-solution-home-credit - source code and for Home Credit Default Risk.
Build faster with AI coding agents. Factory Droids automate coding, testing, and deployment for startups and enterprises.
Falcon-40B-Instruct is a 40B parameter causal decoder-only model built by TII based on Falcon-40B and finetuned on a mixture of Baize, released under the Apache 2.0 license. It is intended as a ready-to-use chat and instruct model, and the card notes it may not be ideal for further finetuning. The model is trained mostly on English data, and users are advised to take precautions for production use.
FlexApp is an AI mobile app designer offered by GenDesigns that generates polished mobile user interface screens from text descriptions of app ideas. The tool requires no prior Figma experience or design skills to use, and provides access to a library of public community app and template projects. It is designed to streamline the mobile app UI creation process.
Floom is an open-source orchestration and execution tool for Generative AI pipelines, described as "The K8s for AI" and aimed at Developers and DevOps. Its repository is MIT licensed and the README states that Floom is now open-source and free for everyone, including commercial use.
FlowiseAI is an open source generative AI development platform for visually building AI agents and LLM orchestration systems. It offers features including multi-agent workflow orchestration, chat assistants with retrieval-augmented generation support, human-in-the-loop task review, execution tracing, and APIs, SDKs and embedded chat options for integration. The project notes it is being sunset.
fractal is a tool for hierarchical agent loops with recursive self-organization, in which autonomous agent loops arrange themselves into a tree of git worktrees and spawn child nodes for separable subtasks. Hard caps on iterations, depth, children, cost and time bound each loop, and run metadata, including cost, is stored in a local SQLite database. Nodes run their agents without permission prompts by default.
Future AGI SDK is a production-grade software development kit for AI evaluation, prompt management, and observability. It offers automated evaluations with sub-100ms guardrails and does not require human-in-the-loop. The SDK supports Python and TypeScript.
Gemini CLI is a terminal-based tool that brings Gemini models into the local development environment. It can query and edit large codebases, generate apps from images or PDFs, and automate workflows. Documentation covers configuration, extensions, agent skills, and IDE integration. Release channels include nightly, preview, and stable.
