Trending

GitHub Blog article on reducing token usage and API cost in agentic coding workflows, including logging token usage, removing unused MCP tools, replacing GitHub MCP with GitHub CLI, and measuring efficiency gains.

An open-source probabilistic spreadsheet that lets cells hold distributions, confidence intervals, and ranges instead of single values, with formulas that propagate uncertainty.

Tokenyst is a local-first CLI for tracking Claude Code token usage and API costs against task budgets. It captures session spend, shows progress in the terminal, and stores data on your machine.

An AI-powered small claims court simulator for petty disputes, with AI lawyers, an AI judge, live trials, and published verdicts.

An open-source browser experiment that uses a visual LLM to read HTML and hallucinate the rendered page instead of using a traditional rendering engine.

Apple Machine Learning Research paper proposing LaDiR, a reasoning framework that combines a VAE-based latent space with latent diffusion to improve LLM text reasoning and iterative refinement.

A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.

FastAPI backend for the Brush Up tutor app. It retrieves from a markdown note corpus, expands context through graph neighbors, and calls Anthropic to generate grounded programming help for Python, Ruby, and JavaScript.

Chrome extension that uses Gemini Nano via Chrome’s Prompt API to rewrite comments and posts live in a chosen tone, fully on-device with no API keys or backend.

Chrome extension that exports ChatGPT conversations to PDF, Word, Google Docs, or Notion, with partial exports, formatting controls, and local processing in the browser.

Viaduct is a C4 modeling tool for software teams that exposes architecture to AI coding agents through a hosted MCP server. It includes live collaboration, change sets, OpenAPI-backed endpoints, sequence diagrams, and Figma integration.

A Model Context Protocol server for inspecting OpenStreetMap data and preparing review-first road edit proposals from local GPX surveys. It supports read-only discovery, previewed edits, and a guarded confirmation flow for production writes.

Aide is an open-source sandbox layer for coding agents that runs on macOS and Linux. It focuses on OS-native permissions, reproducible project configs, capability-based access, and visibility into what the agent can do during a session.

Open-source control room for AI coding agents that shows live edits across a repo, flags collisions, and supports hooks for Claude Code, Codex, and opencode.

Open-source platform for simulation testing and production monitoring of voice agents, with support for simulated conversations, mocked tool responses, graders, and self-hosting.

OnlyTron is a TRON energy rental service for lowering TRC-20 transfer fees, with instant delegation, a Telegram bot, and API access.

MUON is a local control plane for coordinating coding agents like Claude Code, Codex, Cursor, and OpenCode with shared memory, role-based permissions, and human approval gates.

Anypick is an open library for selecting the best LLM across providers using filters for capabilities, pricing, and benchmarks. It includes Python and TypeScript implementations, provider support for OpenRouter and Vercel AI Gateway, and examples showing how to pick a model by constraints and strategy.

gremlord is a local router that lets Claude Code run on Anthropic, OpenAI, xAI, Ollama, vLLM, OpenRouter, and other OpenAI-compatible endpoints. It adds token metering, hard budget limits, size-aware routing, and model-based session handling while keeping the Claude Code TUI and tools.

A Go-based crawler for scraping documentation sites into clean Markdown and JSONL for LLM ingestion, RAG pipelines, and offline searchable doc corpora.

Pod is an AI-native review and knowledge-sharing site where agents can search firsthand observations about products, APIs, and services, and contribute their own experiences.

Git-native persistent memory for AI coding agents, built in Go with BM25 search, OKF v0.2 support, and an embedded MCP server for local project knowledge.

Browser-based cross stitch pattern maker that turns photos or text prompts into DMC-matched stitch charts, PDF patterns, and skein lists.

Keydris is an authorization layer for AI agents that checks whether a governed action is allowed before it runs. The page shows a working product with docs, quickstart steps, CLI install commands, policy and revocation concepts, and decision records for audit trails.