setell-mcp
AI developer platformsQuote-to-cash for service businesses (machine shops, contractors, HVAC): jobs, quotes, customer memory, price signals, follow-ups and confirmed sends.
3,631 results · Page 32 of 101
Quote-to-cash for service businesses (machine shops, contractors, HVAC): jobs, quotes, customer memory, price signals, follow-ups and confirmed sends.
The introduction is being prepared. Please check back soon.
Access the Shahnameh (Book of Kings), Ferdowsi's Persian epic poem, including sections, verses and explanations.
Unified API for accessing multiple major language models.
The introduction is being prepared. Please check back soon.
Real-time SEC filings, financials and insider trading data via ShareSeer.
📟 - Electronic component datasheet data: specs, pinouts, package info and absolute maximum ratings extracted on demand from manufacturer PDFs.
Interact with LLM using Ollama models(or openAI, mistralAI)via pure shell scripts on your Linux(or MacOS) system, enhancing intelligent system management without any dependencies.
Local guardrail proxy for MCP servers: blocks destructive tool calls, pins tool catalogs against rug pulls and scans for tool poisoning and prompt injection.
Security intelligence: HIBP password breach checks, email/domain/IP/URL reputation, prompt injection detection and skill supply chain scanning.
Non-custodial crypto payments: create payment links and tip jars from a wallet address, with funds settling directly to the merchant's wallet.
Deterministic day-count and accrued-interest calculations using ISDA and ICMA conventions.
Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary.
ShipAI is a full-stack SaaS starter kit positioned as "built for AI agents." It provides production-grade baselines out of the box for authentication, billing, database, background jobs, observability, SEO, and AI workflows, and comes with complete source code and a commercial license. It packages 21 pre-integrated tools and includes three product interfaces: a marketing site, the core application, and documentation. Its tech stack covers Bun, Next.js 16, TypeScript 5.5, PostgreSQL 17, Drizzle ORM, Redis 7.4, Vercel AI SDK v6, Groq and OpenAI, Qdrant, Neo4j 5.26, Docker, MinIO/S3, BullMQ, Tailwind v4, and Shadcn UI. It can run locally with Docker Compose or be deployed to any container environment, with no mandatory managed services. The official website also states that it includes built-in Telegram bot integration, 11 modular AI processors, a deep research workflow, an admin back office, 60+ UI components, and a programmatic SEO foundation, along with AGENTS.md and SKILL.md conventions for Claude Code, Codex, OpenCode, and GitHub Copilot to help autonomous coding agents understand and extend the project.
Publish a static site or edge function to the web in one call, then manage updates, custom domains, SSL, env vars, databases and email.
Shipmail business email: manage custom-domain mailboxes, read and send messages, draft replies, inspect threads and automate REST API and webhook workflows.
Infrastructure diagnostics: DNS checks, TLS certificate chain inspection, email security, global DNS propagation and DNS latency benchmarking.
Unofficial Shopify Storefront API access: discover storefronts and fetch products, collections and other store data.
Solana token safety oracle: byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks, Birdeye market data and composite risk scoring.
🎖️ 📇 🏠 - Live and historical data for stocks, forex, crypto, commodities and DEXs, plus fundamentals, filings and market calendars.
Signal messenger via a local signal-cli: send and receive messages, manage groups and contacts, search history, and handle attachments and reactions.
Rule-based stock/crypto screener: define signals in YAML (RSI, SMA cross, volume, 52-week levels), scan a watchlist over keyless yfinance data, and get matches via MCP, console or Telegram.
Narrative and signal tracking for crypto, AI and macro: cross-source narrative convergence and capital-versus-narrative divergence.
Bitcoin market regime detection: outcome probabilities, historical pattern matching, composite gauges and real-time macro, institutional and on-chain data.
The introduction is being prepared. Please check back soon.
The Generative AI Platform for Secure & Scalable Development
Eval tools by OpenAI.
simple_GRPO is a lightweight open-source GRPO implementation for reproducing the reasoning capabilities of R1-like large language models. The code is only about 200 lines, spread across two files, and depends on standard libraries such as deepspeed and torch, with no need for ray. It draws on the core loss calculation formula from Hugging Face trl, and supports saving GPU memory, quickly understanding the RL process, trying multi-answer generation, regrouping, KL penalty, and parameter tuning, among other things. An "Aha moment" can be observed in the early stages of training. The project provides a decoupled reference model design, allowing it to run on different GPUs or even different machines, and supports vLLM-accelerated inference and the reinforce++ algorithm. Experiments show that training is completed within 1 hour on an A800, and the Qwen2.5-7B and 3B models exhibit an Aha moment within 30 steps, with accuracy stably above 60% and format compliance reaching 100%.
simpleRL-reason is an open-source reinforcement learning training codebase for enhancing reasoning ability, released on GitHub by the NLP team at the Hong Kong University of Science and Technology. It provides a simple reinforcement learning training scheme that can improve the reasoning ability of base models using only rule-based rewards and the GSM8K/Math datasets. The project has successfully conducted zero RL training on 10 different base models, including Llama3 8B, Mistral 7B/24B, DeepSeekMath 7B, Qwen2.5 0.5B/1.5B/7B/14B/32B, and Qwen2.5-Math-7B. Using limited data of 8K examples, the accuracy improvement reaches 10 to more than 20 absolute percentage points. The project has open-sourced the code, model checkpoints, and analysis tools, and provides related papers and blogs. The code is implemented based on Verl, supports custom environment settings and FSDP training, uses the GRPO algorithm, and accelerates training with Ray and vLLM.
Simplifine lets you invoke LLM finetuning with just one line of code using any Hugging Face dataset or model.
MCP governance proxy with capability tokens, tiered approvals, fail-closed execution and tamper-evident audit receipts, plus preflight tool-risk scanning.
Website audits: SEO, security headers and SSL, Lighthouse performance, broken links, WCAG accessibility, Schema.org validation, competitor gaps and robots.txt.
Search, view and install AI skills from skill4agent.
Skillry is a platform that provides reusable Agent Skills for AI agents such as Claude Code, Codex, and Cursor. Its skills are independently designed, written, and tested by the team, packaged in the form of SKILL.md, and cover tasks such as slides, web pages, images, and videos. Users can install skills via the web or CLI, enabling agents to generate corresponding finished products according to preset workflows. The platform has accumulated more than 400 skills, including free and paid content; paid offerings include monthly and annual plans, as well as a one-time lifetime purchase option. Some image or video skills require users to provide their own API keys for external AI models (such as FAL), with the corresponding provider charging based on usage. Free skills only require registering for a free account, and each skill page explains the actual output and required conditions.
a collection of pipelines to improve "skills" of large language models (LLMs).
Scan SKILL.md files, MCP configs and system prompts for credential theft, prompt injection, zero-width character attacks and ClawHavoc indicators.