Newly Accepted

LiteLLM is moving its AI gateway to Rust and claims major gains in throughput, memory use, and request overhead while keeping the same config, API, and provider coverage.

Open-source AI agent monitoring platform with tracing, issue grouping, evals, semantic search, alerts, and MCP access for coding agents.

OpenBot is a local-first harness for running AI agents. It includes a small event API, local file storage, a built-in orchestrator agent, a deterministic state agent, and support for custom agents and plugins loaded from disk.

An Android accessibility service that lets agents and scripts inspect the UI tree and control a phone from the CLI, REST, or MCP with token-gated permissions.

Cachet is a local semantic cache for LLM APIs that sits in front of OpenAI- or Anthropic-compatible endpoints and serves repeated or rephrased requests from cache. It includes a dashboard for hit rate and estimated savings, supports streaming responses, and is implemented as a single Rust binary.

Open-source CLI and plugin that lets Claude Code run workflows, teams, and subagents on third-party models like DeepSeek, GLM, Kimi, Qwen, or Codex-compatible providers.

Open-source CLI and TUI for auditing Claude Code skills: shows usage heat, token cost, broken skills, and relationship graphs, with JSON/Markdown output for CI.

Aharness is an open-source workflow harness for Codex that turns coding-agent processes into enforced state machines with typed gates, validated evidence, controlled transitions, repair paths, and inspectable logs.

Buzz is a self-hostable workspace for humans and AI agents to collaborate in the same threads, with signed events, audit trails, channels, workflows, and code-oriented actions.

An ICML 2026 research project page arguing that prompt injection comes from how LLMs misread roles, with an extended writeup, examples, and links to the paper, code, arXiv, and BibTeX.

An OpenAI-compatible LLM proxy that routes requests to the fastest healthy provider. It runs as a small sidecar, supports latency/error-aware routing, session affinity, and Vertex AI, and can be deployed as a single static binary or Docker container.

Open-source MCP server and CLI that lets an LLM control hardware workflows like compiling, flashing, and reading serial output for firmware development and device diagnostics.

GreyFox Community Edition is a self-hosted AI traffic proxy and admin console for teams that want to control LLM usage, enforce per-user quotas, reuse cached responses, and keep traffic inside their own infrastructure.

Local-first desktop ETL/ELT studio with a drag-and-drop pipeline canvas, DuckDB execution, and an on-device AI assistant for describing workflows in plain English.

Local-first persistent memory for AI coding agents over MCP. PMB stores decisions, lessons, project facts, and searchable context in a single SQLite file and exposes it through a CLI and dashboard.

A governed memory runtime for AI assistants with typed storage, policy checks, audit logging, tenant isolation, and hybrid retrieval. The repo includes a backend API, worker jobs, SDK examples, architecture docs, and eval harnesses.

Local-first CLI that records a debugging session and turns it into an evidence-backed Markdown report for PRs, handoffs, and incident notes. It captures commands, notes, exit codes, and git context, then generates a timeline and red-to-green summary from the recorded evidence.

Ponytrail is a CLI and bundled agent skill for tracking why files changed, viewing a local history tree, and reverting snapshots in AI coding workflows.

A write-up of a custom French-learning system built around spaced repetition, grammar tracking, and a voice practice app. It explains the problem, the workflow, and the model/API stack used to keep costs low.

Recall is a local-first memory tool for Claude Code that logs sessions and generates a compact project summary offline, without sending data to an API.

A web app that generates product or project ideas by pairing familiar tools with an added agent layer. The page frames it as an idea generator for “copy idea” style prompts, with a simple call to action to pull the lever for a new departure.

AdvertBench is a web app for ranking AI-generated image ad sets with Elo voting. The page shows head-to-head ad comparisons, a leaderboard, and a sample prompt for generating ads, making the product purpose easy to understand.

Didon is an AI-powered automatic time tracker for macOS that turns screen activity into daily work logs, project breakdowns, and productivity insights. It runs locally with on-device AI, supports CSV exports, and is positioned for people who want automatic journaling without manual timers.

Whitman is a Rust CLI for selecting an AGENTS.md profile and linking it into the current project. It supports interactive profile browsing, profile creation, and safe symlink handling across local projects and Git repositories.