Policy Optimization for Generative Models: diffusion and flow policies, online fine-tuning, and inference-time guidance and planning.
☆101Oct 1, 2026Updated 2 weeks ago
Alternatives and similar repositories for POInfra
Users that are interested in POInfra are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MyCareer Agent——你的全流程秋招/春招求职Agent助手:岗位采集、简历分析与定制、公司调研、投递管理、面试准备和模拟面试☆110Updated this week
- 从 0 训练大模型,单卡训练一个 200M 参数模型的全流程(train a 200M‑parameter model from scratch)☆62Sep 23, 2026Updated 3 weeks ago
- ☆71Updated this week
- ☆300Aug 18, 2026Updated last month
- Session strata for the DeepSeek Harness Web GUI: the transcript's scrollbar becomes a to-scale, colour-coded map of the whole run, with y…☆101Sep 11, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A LangGraph-powered repository agent that uses LangChain, Q-learning, and human approval to plan, patch, test, and adapt code changes saf…☆102Aug 21, 2026Updated last month
- ☆92Updated this week
- A persistent LLM-maintained knowledge system for technical manuals, SOPs, and operational documentation.☆180Sep 16, 2026Updated last month
- Coordinate multiple AI coding agents through a local-first, recoverable Agent Bus.☆100Updated this week
- 一个带有知识库功能的ai聊天工具,试作,自用☆124Sep 6, 2026Updated last month
- ☆820Updated this week
- A routing protocol suite in Rust — router + Rust.☆27Updated this week
- 一条命令,把口播毛片变成可二次精修的剪辑工程。☆711Updated this week
- 「EMNLP2026 Findings」AsyncTool is a benchmark for evaluating the asynchronous function-calling capability of LLM-based agents in multi-tas…☆102May 27, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retri…☆101Oct 8, 2026Updated last week
- TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming☆354Aug 24, 2026Updated last month
- ☆76Updated this week
- Open-source mission control for coding agents. Run cross-vendor workers in isolated worktrees, audit every submission, and revert an enti…☆116Oct 1, 2026Updated 2 weeks ago
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,006Updated this week
- 希儿最初的家~☆796Updated this week
- Reinforcement learning framework for tool-augmented multi-answer question answering with step-wise peer advantage and diversity-aware exp…☆142Aug 1, 2026Updated 2 months ago
- Using for capturing field experiment data and images by your Android phone☆98Aug 13, 2026Updated 2 months ago
- Caddy Reverse Proxy Balancer WebUI☆406Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 跨平台 P2P 协作绘图应用:二维码配对即连、无需账号,TURN 兜底穿透对称 NAT,端到端加密(Kotlin Multiplatform / Compose Multiplatform / DrawBox)☆100Updated this week
- Convert ONNX models to Apple Core ML (.mlpackage / .mlmodel) with numerical-parity verification against ONNX Runtime.☆153Jun 17, 2026Updated 4 months ago
- A custom Agent OS built to be hackable, heavily inspired by OpenClaw.☆484Aug 7, 2026Updated 2 months ago
- MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端,用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上,不依赖任何远端服务。☆874Updated this week
- 般若波罗蜜。回到每一个争吵和沉默的节点,看看另一个版本的结局。☆875Sep 17, 2026Updated last month
- 🧠 NeuroConscious Transformer (NCT) - A next-generation neuromorphic consciousness architecture integrating Transformer with Global Works…☆468Aug 1, 2026Updated 2 months ago
- Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.