Top Picks

Open-source, self-hostable sandbox for AI agents. It lets agents work inside isolated Linux containers through MCP tools, with CLI and host-level admin controls for creating, managing, and exposing boxes.

Open-source infrastructure for running and automating sandboxed coding agents, with local Docker setup, integrations, snapshots, sessions, and automations.

A loadable SQLite extension that adds column-oriented storage and analytics for fast local OLAP-style queries, with benchmark data and build instructions.

A Rust-based hybrid local code search tool for developers and AI agents, with BM25 + semantic retrieval, persistent indexing, tree-sitter symbol search, and MCP/gRPC integrations.

OpenWorkers is a thesis-focused research assistant that searches literature, verifies citations, critiques ideas, and produces structured research support without writing the prose for the student.

Semble is a local-first code search tool for agents. It offers natural-language search, an MCP server, bash/AGENTS.md integration, and a Python API, with claims of faster indexing and much lower token usage than grep+read.

Patchwork is a Rust CLI for AST-native code refactoring without LLMs. It can find, replace, delete, and insert code by structure instead of regex, with support for Java, Python, JavaScript, TypeScript, and TSX.

Open-source agentic mesh for governing AI agents across enterprise systems, with identity, policy enforcement, audit trails, observability, and Kubernetes-native deployment.

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.

A CLI for the Slack Web API built for coding agents. It exposes Slack methods through a single command format, supports JSON stdin, dry runs, pagination, and discovery commands, and installs via npm.

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.