Upvoted Tools

Self-hosted open-source AI API server that exposes unified REST endpoints and supports multiple LLM providers for integration into applications.

Privacy-preserving decentralized intelligence: attested TEEs + Solana PDAs for on-chain sessions and payments, with an open marketplace of service agents.

Automated evaluation and monitoring platform that scores, detects failures, and optimizes LLMs and AI agents using evaluation models, experiments, traces, and an API/SDK ecosystem.

Run Claude Code tasks in isolated cloud VMs from your browser, working directly against your GitHub repos and auto-opening PRs when done.

AI-native product analytics platform that connects directly to your Supabase database to deliver instant dashboards, insights, and reports without a data team.

Mastra is an open-source TypeScript framework for building AI-powered applications and agents, with built-in support for workflows, RAG, memory, MCP, evals, and observability.

End-to-end, open-source recipe to train and serve a small chat LLM (~560M params) for about $100 on one 8×H100 node, with tokenizer, pretrain→midtrain→SFT→optional RL, FastAPI web UI, and a KV-cached inference engine.

GH Copilot graduated into its own CLI. Not a rename—an upgrade. It’s now an agent that can understand your repo, propose edits, run commands, and even open PRs—with approvals.

100-line Python coding agent with CLI/TUI that fixes GitHub issues and automates repo tasks. Model-agnostic via LiteLLM, sandboxable (Docker/Podman/Bubblewrap), with an Inspector to browse trajectories.

AI coding assistant plugin for Qt Creator: chat, code review, tests, docs, and smart completions for C++/QML/Python with cloud or local LLMs.