Newly Accepted

A file-backed workflow for resumable coding-agent projects, using Markdown records, a CLI, and bundled workflow skills to keep project state on disk instead of in chat.

A GitHub research project that measures how gpt-4.1 responds when asked to pick a random number between 1 and 100, using 10,000 API calls and comparing the results to a uniform baseline.

An interactive guide for choosing local AI hardware and matching open-weights LLMs to specific builds. It offers budget-based build recommendations, a hardware picker, model-to-hardware compatibility, and a state-of-the-local-AI snapshot.

A PyTorch reference implementation of DeepSeek Sparse Attention from the LLMs-from-scratch project, including a lightweight indexer, top-K token selection, and a GPT-style model with KV-cache support.

CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.

A Mojo port of the Pi AI Agent Toolkit with a set of runnable examples for chat, coding agents, tool calling, web research, and long-running agent loops.

A browser-based demo where an AI agent writes x86_64 assembly and eBPF to generate Wolfram cellular automata and Mandelbrot fractals inside a real Linux VM, with framebuffer and kernel trace streams exposed live.

An essay arguing that second-person system prompts create attentional overhead and identity fragmentation in agent design, and proposing first-person initialization as an alternative.

Agenvoy is a Go-native multi-model AI agent framework that routes tasks to the best model, shares a common daemon and session across interfaces, and can generate scripts or APIs to extend its toolset.

Optic is an AI feature intelligence platform for SaaS teams. It tracks AI interactions at the account level, surfaces quality and abandonment signals, and sends engineering alerts plus daily CS digests in Slack.

A bilingual satirical idle simulation where you run an AI startup from toy classifiers to near-AGI, managing data, compute, launches, crises, and rivals.

A Torque demo page showing proof-gated, policy-checked production changes for a Kubernetes PostgreSQL workload, with signed evidence, authorization records, and replayable audit artifacts.

Local-first memory layer for coding agents with an MCP server, CLI, and desktop console for durable project context, handoffs, and recall across sessions.

OpenClaw is a self-hosted personal AI assistant that runs on your own devices and connects to many messaging channels, with CLI-based setup and onboarding.

A docs index page for Claude Code that maps the documentation structure and links to major sections like getting started, core concepts, tools, automation, and deployment.

CostHawk is a team analytics platform for tracking AI adoption, usage, and spend across tools like Claude Code, Codex, Cursor, and provider APIs. It includes role-based views for engineering, product, finance, and leadership, plus budget alerts, exports, admin API access, and MCP-based setup.

Git-native memory for coding agents that stores repo intent, decisions, constraints, and review context before the diff. The repo includes the problem statement, product positioning, install steps, and agent hooks for tools like Claude Code, Cursor, and Codex.

Research paper introducing hyperagents, a self-referential agent framework that combines a task agent and a meta agent into one editable program. The abstract describes a DGM-based system that improves both task performance and its own improvement process across domains.

A secure Model Context Protocol server that gives AI assistants controlled terminal access with risk analysis, sandboxing, logging, filesystem protection, and optional Docker and Git features.

An experimental programming language and compiler built for agent workflows, with CLI commands for parsing, checking, graphing, repair planning, and JSON-based inspection output.

AWS DevOps blog post explaining how to build a self-extending CLI using Amazon Bedrock, the Strands Agents SDK, and MCP. It outlines the workflow, technical pieces, and repository availability for readers who want to replicate the pattern.

An open-source MCP server for controlling macOS with AI agents. It supports file navigation, app control, UI interaction, browser automation, and system operations, with setup instructions and client integrations for tools like Claude Desktop and Gemini CLI.

Rust TUI for browsing local Codex and Claude Code session logs, searching past chats, and estimating API-equivalent cost.

A terminal multiplexer built for AI coding agents, with persistent sessions, agent-aware status, remote attach, and workspace/tab/pane management.