Top Picks

A Claude Code plugin that turns waiting time into a terminal Pokémon mini-game. It shows wild Pokémon while Claude works, runs locally, and includes install steps plus update behavior.

Live pricing and cost calculators for 232+ AI models, with monthly bill estimates, token math, and vendor-by-vendor price tables.

DSCode is an open-source coding agent for working in real repositories from the terminal. It supports install via npm, connects to DeepSeek, and highlights local sessions, sandboxed commands, parallel agents, and cost tracking.

PipeCrab is an open-source Rust pipeline for building voice agents, with local inference support and examples that show end-to-end audio, transcription, LLM, and TTS flows.

A Lean 4 relational knowledge language for project relationships, rules, and queries, with a Clojure runtime/toolchain and examples inspired by Zanzibar.

A Lean 4 project for formally verified 3D mesh intersection and constructive solid geometry, with a browser demo for intersecting example meshes or STL imports.

A language server for agent skills that turns /skill-name and $skill-name into navigable symbols with completion, rename, go-to-definition, and reference tracking across editors like VS Code, Zed, Neovim, and Helix.

Open-source resilience and debugging proxy for autonomous AI agents. It checkpoints LLM and tool calls, supports cache recovery, human-in-the-loop approval, multi-model fallback, and exports trajectories for fine-tuning.

Local-first approval and receipt logging for AI agent sessions, with tamper-evident records and signed approvals for consequential actions.

Dependency-free Python library that compiles a declarative JSON query format into safe, parameterized SQL for LLM workflows, REST APIs, and frontend-backed data tables.

Open-source TypeScript crawler for AI agents that needs bounded web access, structured extraction, PDF parsing, JavaScript rendering, and MCP support. It outputs Markdown, JSON, and JSONL evidence records with provenance and crawl limits.

A local CLI tool that keeps Claude Code sessions warm by refreshing prompt cache during long subagent runs, aiming to reduce re-encoding costs in extended sessions.

Jaybase is an append-only fact store for AI agents handling critical business workflows. The repo explains its event model, retry and conflict handling, encryption, single-tenant design, and includes install and API usage examples.

Local, structured memory for AI coding assistants like Claude Code and Codex. The project stores decisions, constraints, and abandoned approaches in an event-sourced local log and injects them back into later sessions.

ContextSpy is an LLM context profiler that intercepts agent traffic, breaks down token usage, and visualizes how prompts change across requests and sessions.

Local open-source coding agent for developers, with a macro-style command workflow and benchmark results showing fewer turns and better pass rates than Codex CLI in the published comparison.

A Python framework for local document search that replaces traditional embedding-based RAG with BM25 indexing, Meilisearch, and an agent loop for search, fetch, and citation-backed answers.

A browser-based clicker game where local AI builds a custom game from your idea entirely on-device via WebGPU, with no API keys or servers.

Persistent memory for coding agents that stores hard-won codebase discoveries and revalidates them when files change. The repo describes a CLI hook flow for Claude Code and Codex, with install steps, command examples, and an evaluation claim showing fewer tokens on repeat questions.

An AI-powered Obsidian plugin that turns notes into a self-organizing wiki with auto-generated entity pages, bidirectional links, traceable answers, and local-first support.

Google Workspace Marketplace app that translates documents, web pages, and chat text with layout preservation and AI writing support.

A harness that runs MCP servers in a disposable Linux sandbox and logs their real startup behavior, including file access and outbound network connections.

Fenzo AI generates interactive micro-courses from a question, topic, or uploaded notes. The page shows live lesson examples, a learning-focused product pitch, and use cases like exam prep, concept explanation, and community-created courses.

Open-source Kubernetes-native runtime for LLM agents. CLRK runs agents in gVisor sandboxes and intercepts outbound traffic for observability, policy enforcement, credential injection, and routing control.