Directory
Published directory entries matching your search.
DeepSeek Coder is a series of open code language models trained from scratch on 2T tokens, composed of 87% code and 13% natural language in English and Chinese. Models are offered in 1B, 5.7B, 6.7B and 33B sizes, pre-trained on project-level code corpora with a 16K window size and a fill-in-the-blank task for completion and infilling.
Qwen3-Coder is the code version of the Qwen3 large language model series from the Qwen team. It is offered in multiple sizes, including Qwen3-Coder-480B-A35B-Instruct, Qwen3-Coder-30B-A3B-Instruct and Qwen3-Coder-Next, and the repository supports platforms such as Qwen Code, CLINE and Claude Code.
Supermaven is an AI code completion tool that uses a 1 million token context window to provide code suggestions. It is compatible with VS Code, JetBrains IDEs and Neovim, and includes a chat interface for working with models including GPT-4o and Claude 3.5 Sonnet. A free tier is offered, and Pro adds a 1 million token context window.
Open-source coding assistant using language models and vector embeddings to search, retrieve, explore and understand codebases. It works with local code and multiple programming languages; code snippets are only transmitted when a question is asked. Installation is via pip, and it defaults to the gpt-3.5-turbo-16k model.
A repository holding the paper source, analysis notebook, and data generation and analysis scripts for the diginorm paper. It is forked from another repository and includes LaTeX sources, bibliography files, figures and a pipeline folder.
Annotation Lab, referenced in its 4.10 release notes as NLP Lab 4.10, is a platform from John Snow Labs for annotation tasks. The 4.10 release added features including in-app trial license generation, enhanced commenting and tagging for labeling pages, improved task export filters, a video template for project content types, and fixes for visual NER task export JSON formatting.
Creates or edits images with generative models and visual controls.
daspartho/prompt-extend is a publicly hosted GitHub repository for a tool that extends Stable Diffusion prompts with appropriate style cues using text generation. The repository includes documentation for usage, code files, example prompts, and contribution guidelines for the project.
Flux is the official inference repository for FLUX.1 models from Black Forest Labs. It contains minimal inference code for running image generation and editing with the open-weight models, including text-to-image, in/out-painting, structural conditioning and image variation variants. The repository is distributed under the Apache-2.0 license.
PandasAI is an open-source library that enables conversational data analysis using large language models and retrieval-augmented generation. It allows users to interact with databases or datalakes supporting SQL, CSV, and parquet file formats.
Kiln AI is a platform and open-source library for building, evaluating, and optimizing AI systems. It offers tools for working with retrieval-augmented generation, AI agents, synthetic data, model fine-tuning, and prompt optimization, with a free downloadable application available for macOS, Windows, and Linux.
Melies is an AI studio for filmmaking that generates images, videos, movie posters, voices, music and sound effects. It offers 30+ AI models and a library of 150+ AI actors. A CLI is available for image, video and movie poster generation from the command line. Plans include monthly credits.
MusicGen is a single-stage auto-regressive Transformer model for music generation trained over a 32kHz EnCodec tokenizer with four codebooks, part of the AudioCraft library. It supports text-to-music and text-plus-melody-to-music models ranging from 300M to 3.3B parameters. Running it locally requires a GPU, with at least 16 GB of memory recommended for medium-sized models.
The FLUX.1 family of models on Replicate is a collection of Black Forest Labs' FLUX AI models for image generation and editing. Users can run the models with one line of code, fine-tune them with custom data, and edit images using Flux Fill, Depth, and Canny tools. The collection includes multiple FLUX model variants suited for different use cases.
WFGY is an open-source project focused on AI reasoning, retrieval-augmented generation, AI agents, and real-world workflows. It is developing the WFGY 5.0 Polaris Protocol, and currently includes components such as the Problem Map, Global Debug Card, 4.0 version, and CFV Easter Egg.
A transcription API built on OpenAI Whisper that converts audio and video files to text. It supports file uploads and remote URLs, multiple output formats, and model size selection for speed versus accuracy. A no-code dashboard offers drag-and-drop transcription. Pricing is pay-as-you-go with credit bundles, and files auto-delete after 24 hours.
YobiYoba is a speech recognition service that transcribes audio and video recordings into editable, time-coded text. Users upload files, specify or auto-detect the language, verify and edit transcripts, then download them in formats such as SRT, PDF, or VTT. Processing produces speaker labels, time codes, and confidence scores. Pricing is pay-as-you-go, from 0.01 € per minute of speech.
AI/ML API provides access to over 1000 AI models through a single API for text, image, video, audio, code and embeddings, with pricing, latency and capability comparison in one place. It also offers an MCP server for connecting clients such as Claude, Cursor and Claude Code.
Aider is an AI pair programming tool that runs in the terminal and works with cloud and local LLMs. It maps the codebase, supports more than 100 code languages, and integrates with Git to automatically commit changes. It can also run in an IDE and accept voice-to-code instructions.
Amadeus Code provides music AI infrastructure spanning rights-cleared training data, audio supply and royalty management. Its products include MusicTGA for MIDI songwriting ideas, FUJIYAMA AI SOUND for music and sound materials, and Evoke Music, a royalty-free library. CONNECT is a royalty management platform for copyrights and master rights in Japan.
automl-gs is a Python 3 AutoML module that takes an input CSV and a target field and generates a trained machine learning or deep learning model plus native Python code pipelines. It provides a zero code/model definition interface and performs random hyperparameter searches, reporting metrics for each trial in a CSV.
Claude Code is Anthropic's agentic coding tool for developers. It understands a codebase, edits files and runs commands. It is available as a terminal, IDE, Slack or web tool for macOS, Linux and Windows. Projects group related coding sessions so multiple Claude agents can run at once, and auto mode runs by default on Pro, Max and Team plans.
CodeRabbit is an AI-first pull request reviewer. It provides context-aware feedback, line-by-line code suggestions, real-time chat, and agentic change management features including PR triage, code explainability, and security monitoring for agent outputs.
awesome-vibe-coding is a curated GitHub repository maintained by filipecalegario that compiles references for vibe coding, the practice of collaborating with AI to write code. The list includes resources for browser-based tools, IDEs, and code editors relevant to this development approach. The repository accepts community contributions.
