SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,641 results · Page 87 of 102

PR1

AI developer platforms

Perception-R1 (PR1) is the official code implementation of the NeurIPS 2025 paper, proposing a scalable reinforcement learning framework that post-trains multimodal large language models (MLLMs) via Group Relative Policy Optimization (GRPO) to enhance visual perception capabilities. Its core innovations include: perceptual perplexity analysis, used to reveal the key threshold for effective reinforcement learning in perception tasks; rule-based reward shaping and GRPO optimization, enabling scalable policy learning; and significant improvements on multiple visual perception benchmarks, for example reaching 31.9% mAP on the COCO2017 validation set, becoming the first 3B-scale MLLM to achieve this performance. The project provides training and evaluation code, supports tasks such as grounding, counting, and detection, and users need to configure model and data paths themselves and separately download COCO images.

Read more

prime-rl

AI developer platforms

prime-rl is a training framework for large-scale reinforcement learning (RL), supporting asynchronous RL and agent training. It uses FSDP2 for training and vLLM for inference, scales to 1000+ GPUs, supports 1T+ MoE models, multi-node Slurm deployment, multimodal VLMs, end-to-end post-training with SFT/RL/evaluation, and natively integrates verifiers environments through the Environments Hub. The project is licensed under Apache 2.0, with code open-sourced on GitHub, and the community can contribute through issues and PRs.

Read more

private-gpt

AI developer platforms

PrivateGPT is an open-source API layer developed by the Zylon team for building private AI applications on local models. It does not itself run models; instead, it connects via OPENAI_API_BASE to any OpenAI-compatible inference server (which must implement /v1/chat/completions and /v1/models). It provides a standard messages API that follows the Claude API specification (with support for streaming, async, and token counting), file and artifact ingestion, retrieval with citations and agentic RAG, built-in tools (web search, web scraping, code execution), custom tools and MCP connectors, as well as structured access to databases and CSV, embeddings, and orchestration capabilities. The project includes a /ui workbench interface for testing and demos, but the API is the core product. After PrivateGPT went viral in 2023 as an offline document chat proof of concept and surpassed 50,000 GitHub stars, it was refactored in version 1.0 into a formal API layer for private AI applications. It is suitable for developers who want to build production-grade AI applications with local models without relying on cloud APIs, and can be used with inference servers such as Ollama.

Read more