RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
OCR model that handles complex tables, forms, handwriting with full layout.
- ai
- ocr
- document-ai
- document-parsing
Source control for agents. Use multiple coding agents, track their changes and query them in one place
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
TranslatedSelf-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, scheduling, failover, request logs and usage.
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
Quill - A Modern SaaS-Platform Built With Next.js 13
Cross-platform desktop application for content-aware file organization and renaming. Supports local and remote LLMs, preview-based workflows, and fully user-controlled changes.
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
- decision-models
- jev
- laya
- local-inference
不在身边的时候,TA 还在这里。Upload real chat logs, rebuild a digital persona — open-source AI companion with persona distillation, an emotion engine, 11 LLM providers, and a graduation mechanism.
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
云崽系机器人的智能聊天插件
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- llms
- mechanism
- on-policy-distillation
Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.
毒奶博主的自用机场推荐——150GB/14元/月起,Vless/AnyTLS协议支持,透传,IEPL专线加持,稳定低延迟,ChatGPT 等AI工具支持,Netflix等主流流媒体区域限制解锁;
Framework for algorithmic trading
Tracking prompts, feature flags and metadata of Claude Code releases. Subscribe to ↓
Open-source enforcement at runtime that masks sensitive data and blocks destructive commands from AI agents. You change one thing: your agent's port.
A simple Bitcoin trading bot written in Java.
AI/ML Pentesting Roadmap for Beginners
发布前审|发抖音/小红书/视频号前先让 AI 审一遍:哪句踩线、依据哪条官方规则、给能直接用的改法。38 篇真实样本校准判定尺度,80+ 条官方原文引文可查证,你踩过的坑沉淀成本地规则库越用越准。不承诺过审,不教绕审。
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
- agentic-search
- ai-tools
- context-engineering
- dag