SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,662 results · Page 59 of 102

botpress

AI developer platforms

Botpress is an open-source platform for building and deploying next-generation chatbots and assistants powered by GPT/LLM. This repository contains public integrations maintained by Botpress, Botpress Cloud development tools (CLI, SDK, API client), example bots written in a "code as bot" approach using only the SDK and CLI, and plugins on Botpress Studio (coming soon). The team welcomes community contributions in the form of pull requests and issues. For bugs or feature requests for Botpress Cloud, you can create an issue in this repository, but you will get a faster response by communicating on Discord; for issues related to the self-hosted version Botpress v12, you need to check the Botpress v12 repository.

Read more

build_MiniLLM_from_scratch

AI developer platforms

build_MiniLLM_from_scratch is an open-source project whose goal is to build a small-parameter LLM from scratch, completing all four stages—pretraining, instruction fine-tuning, reward model, and reinforcement learning—to achieve a chat model capable of simple chat tasks at a controllable cost. The project uses the bert4torch training framework, with concise and efficient code. The trained checkpoints can seamlessly connect with the transformers package for inference, and the file reading method during training has been optimized to reduce memory usage. Currently, the pretraining and instruction fine-tuning stages have been completed, and DPO alignment is still being tested. The project provides complete training logs for reproduction and comparison, and also includes a self-cognition dataset, allowing customization of attributes such as the robot's name and author. The chat model supports multi-turn conversations. It should be noted that, limited by corpus size, model scale, and SFT corpus quality, the model currently only has simple chat capabilities and does not have the ability to answer complex questions.

Read more

C2C

AI developer platforms

C2C (Cache-to-Cache) is the official code implementation of the paper "Cache-to-Cache: Direct Semantic Communication Between Large Language Models," accepted at ICLR'26. It enables large language models to communicate directly through KV-Cache, bypassing the text generation step. The project projects and fuses KV-Cache between different models, allowing each model to share semantic representations in a more direct way. Official data shows that this method improves accuracy by 8.5–10.5% compared to a single model, improves by 3.0–5.0% compared to text-based communication, and achieves a 2.0x speedup in latency. The project provides the Python package rosetta (named after the Rosetta Stone), offering a general-purpose RosettaModel wrapper, training and evaluation scripts, configuration files, and pretrained C2C Fuser weights, supports multi-sharer model fusion, and provides an online Demo for hands-on experience.

Read more

C3.ai

AI developer platforms

C3 AI is an enterprise AI software company located in Redwood City, California, USA, providing enterprise-oriented AI platforms and applications, with the core concept of "the agentic operating system for enterprise AI," transforming operational data into real-time decisions and scaled autonomous execution. Its products include the C3 Agentic AI Platform, the Enterprise AI Applications suite, and C3 Generative AI, and it provides specialized applications for industries including defense, energy, manufacturing, government, utilities, and healthcare. The company also offers the C3 Code tool, which it claims can build enterprise AI applications in one day. The platform is described as being built on more than 15 years of domain intelligence and has received a Leader rating in The Forrester Wave™ AI Platforms, Q3 2026.

Read more