Newly Accepted

Anthropic help article explaining how Claude marks generated text with embedded watermarks and signed provenance metadata, plus what the markings cover, how to detect them, and key limitations.

An open 45M-parameter agentic LLM for tiny devices, built for tool calling, device use, and structured extraction. It ships as a 14 MB binary and is positioned for phones, wearables, smart home devices, robots, and other low-RAM hardware.

A voice-driven AI murder mystery game set at Blackwood Manor, where players interview suspects, press them on alibis, and solve a locked-room-style case.

An interactive map of 105 AI labs, grouped by research area, geography, lineage, and valuation, with a table view and filters for browsing the landscape.

A live demo and write-up showing a 3.16M-parameter INT4 transformer running entirely in on-chip memory on a Xilinx Kria KV260 FPGA, with measured token rates and hardware details.

AI shopping agent that reviews product links for price manipulation, review authenticity, and seller reputation, then returns a Tick, Clip, or Skip verdict.

Phinq is an open-source runtime governance layer for AI agents that intercepts tool calls, classifies risk, pauses irreversible actions for human approval, and records decisions in a tamper-evident audit log.

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

VS Code extension that provides one interface for running multiple coding agents, including Claude, Codex, OpenCode, Qwen, and Hermes, with session history, diffs, permissions, and tool-call visibility.

Open-source Go control-plane proxy for AI agents that enforces identity, policy, budgets, and audit for MCP and other upstreams, with anomaly detection that can auto-block compromised agents.

A Rust CLI that renders terminal text effects as a single static binary, ported with byte-exact parity from TerminalTextEffects. The README explains usage, build steps, supported platforms, and the project’s fidelity/performance goals.

Open-source self-hosted inference server for agent workloads, with an OpenAI-compatible API, multi-model serving, and production cluster tooling.

TokenSpend tracks AI coding spend and ties it back to shipped work, with GitHub-based PR attribution, team-level reporting, and a live model router with receipts.

Open-source coding agent that keeps a persistent memory of your repo, with a CLI, self-hosted gateway, model routing, and support for OpenAI-compatible and provider-native endpoints.

A set of 20 Claude Code skills distilled from real engineering failures, each packaged as a short rule set with a pre-flight checklist and install instructions.

Pacific Slate is a self-hosted, model-agnostic multi-agent AI assistant with background work, long-term memory, source tracing, and an interface built around cards and a demo monitor. The page also explains the architecture, agent roles, storage boundaries, and how it connects through MCP and an OpenAI-compatible endpo

unYOLO is a framework for building credential brokers and proxies for AI agents. It keeps provider credentials out of the agent, applies local policy rules, supports timed grants and operator approvals, and includes brokers for GitHub, Hugging Face, and approved Unix commands.

A ProtoLink example that stages autonomous agents in a fictional liability tribunal to study how agent-to-agent communication changes decisions, with replayable traces and HTML reports.

An open 30B agentic model from Meta designed to run locally on consumer hardware for coding, function calling, and other always-on agent workflows.

A Microsoft Research paper PDF on agentic coding and GitHub Copilot at production scale. The crawl confirms it is a substantive research document tied to an AI coding product and suitable for a public listing.

Pier gives each coding-agent session its own cloud VM on the user’s AWS account, with parking, resuming, and repo setup built in.

A Go/Python tool for verifying AI audit logs, checking chain integrity, tamper detection, and whether a log is independently anchored outside the producing system.

Google Research article describing Science One Framework, an autonomous research prototype focused on verifiable AI-generated research through evidence chains and claim verification.

arXiv paper introducing ScientistOne, an autonomous research system built around a chain-of-evidence framework to keep claims traceable and audit research outputs for verifiability.