Recently Evaluated

Aquifer is a self-hosted MCP gateway runtime for buffering spiky agent and API traffic. It queues requests durably in SQLite, dispatches them at a configurable rate, and supports both MCP and HTTP adapters with webhook delivery.

AI sales agent for cold outreach that finds prospects, personalizes messages, and follows up across email, text, LinkedIn, and X until someone replies.

An arXiv paper on reducing LLM inference cost for web automation by compiling browser tasks into a deterministic JSON workflow and executing them without repeated model calls.

A CLI tool that shares Claude Code sessions across a team by storing transcripts and memory on an orphan Git branch, so teammates can pull, resume, push, and delete sessions without extra infrastructure.

Lathe generates multi-part, hands-on technical tutorials from prompts and provides a local UI plus CLI workflow for working through them with LLM-assisted skills.

An interactive guide and demo for prompt engineering that shows how analogies, examples, and format-matching can improve LLM outputs.

A minimal native macOS sandbox for running Claude Code or Codex with OS-enforced limits on what the agent can touch.

A cross-platform Claude Code dashboard for tracking usage limits, token spend, and session forecasts in a single binary with no config.

An open-source handbook for production LLM serving and inference at scale, covering GPU fundamentals, KV cache, batching, quantization, speculative decoding, and engines like vLLM, SGLang, and TensorRT-LLM.

Nanocode is a terminal-based AI coding assistant written in Python. The repo shows CLI install and usage instructions, runtime commands, configuration options, supported providers, and a detailed description of its context and file-editing workflow.

A Python MCP server that lets a parent LLM delegate work to named sub-agents defined in YAML, with per-agent prompts, model settings, and downstream MCP tool access.

Omni is a local-first semantic search app for macOS that indexes text, code, PDFs, images, audio, and video on-device. It supports multilingual search, private offline use, and exposes a local endpoint for agents to query indexed files.

A small web app for taking a break from AI and recording a short session away from LLMs.

A lightweight terminal AI sidecar for Zellij that keeps quick questions separate from your main agent session, with local JSONL logging, SQLite search, and multiple LLM provider options.

A custom Iosevka font build inspired by Anthropic Mono, with prebuilt releases and source build instructions.

A MotherDuck blog interview with Wes McKinney on practical AI coding workflows, including spec-driven development, continuous AI code review, and how to keep agent-generated code maintainable.

Local-first agentic coding assistant in Rust with a terminal UI, embedded web UI, phone app, always-on gateway, and LAN grid dispatch across multiple machines.

Public GitHub repository describing how to access a large Powerset Research GitHub dataset through an MCP server or DuckDB. Includes no-auth access, schema-aware SQL use, and example queries for agents and analysts.

Intencion is a product analytics and observability platform for AI agents. It tracks user intent, tool calls, run outcomes, and resolution trends, then turns failures or unmet requests into Linear or GitHub issues.

Jo is a secure programming language designed to help catch prompt injection and other unsafe behavior at compile time by enforcing explicit capability boundaries. The repository shows the language’s security model, code examples, installation flow, and current project status.

arXiv paper on distilling multi-agent debate into a single LLM with a two-stage fine-tuning pipeline. The abstract reports lower token use, comparable or better benchmark performance, and an analysis of agent-specific activation subspaces, with code linked from the page.

Cloud cost awareness for AI coding agents and IDEs, with real-time pricing for IaC changes, cost tradeoff suggestions, tagging fixes, and policy-aware guardrails.

Lowfat is a lightweight CLI tool that filters noisy command output before it reaches an AI agent, with plugins, shell integration, and usage stats for token savings.

An open-source reference implementation for autonomous vulnerability discovery and remediation with Claude. It includes Claude Code skills for threat modeling, scanning, triage, patching, plus a harness for running a recon → find → verify → report → patch pipeline.