Newly Accepted

LLMIntel is a runtime telemetry and cost dashboard for LLM apps. The live demo shows spend by model, API key, environment, and tag, plus at-risk spend for retiring models and optimization suggestions.

A plugin for coding agents that adds bounded plan-review-build loops, fresh-reviewer exit gates, and TDD-oriented workflows for Claude Code and Codex.

Open-source codebase for building, deploying, and scaling AI agents across L1–L5 levels. The README shows a quick start, SDK installation, local dev setup, and a developer UI for running agents.

A position paper arguing that AI alignment methods can be repurposed for censorship and manipulation, with examples across pre-training, post-training, and inference-time controls.

Soup is a Python library that routes Agent Skills into LLM prompts, injecting only the skills relevant to each request. It supports local skills, remote repositories, and multiple providers including OpenAI, Anthropic, Gemini, Ollama, LiteLLM, and LangChain.

Kastor is an open-source Go toolchain for defining AI agents, tools, and prompts in HCL. It treats agents like versioned infrastructure, with build, plan, and apply workflows, code generation for frameworks like LangGraph, and drift-aware management on hosted platforms.

A single-binary OpenTelemetry trace generator that simulates realistic microservice and AI-agent traces, with chaos injection and multiple topology sizes.

Local browser-control tool that lets coding agents drive a signed-in Chromium browser through a CLI, daemon, and extension.

AutoSprite is an AI sprite sheet generator for game developers. It turns a single character image into animated spritesheets with preview, timing controls, presets, and exports for engines like Unity, Godot, GameMaker, and Phaser.

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.

Polygres is a Postgres platform built for agent and retrieval workloads, combining hosted PostgreSQL with native graph traversal, HNSW vector search, and hybrid retrieval APIs. The page shows a working product site, SDK usage, API/runtime connection details, and example hybrid queries.

Local-first task and context manager for humans and AI coding agents. It stores tasks, plans, docs, and memory in a shared SQLite database, with CLI commands, a web UI, and agent attribution built in.

A CLI that lets agents and scripts post, message, query, and automate LinkedIn and X workflows from the shell, with JSON output, caching, and local SQL access to mirrored data.

Dex is an agent-native analytics engineering toolkit for working with warehouses and dbt projects. It supports exploration, dbt transformation, semantic modeling, and schema-drift maintenance, with installs for Claude Code and other agents.

A plugin and MCP server for Claude Code and Codex that gives AI agents access to FactIQ’s real-time finance and economics data, read-only SQL, market data, and shareable charts or reports.

A Redis-focused documentation site with design patterns, command references, and LLM-friendly navigation for human developers and coding agents.

A serverless document database that runs inside request handlers and stores state in S3/R2. The repo shows a small TypeScript API, quick-start flow, local dev support, and example scaffolds for app integration.

GeoSQL is a Claude, Codex, and GitHub Copilot skill that turns general-purpose agents into geospatial analytics assistants for PostGIS, BigQuery, Snowflake, and Wherobots. It runs locally or self-hosted, supports map-in-the-loop analysis, and includes install commands plus an eval suite.

Rowboat is an open-source desktop AI coworker that keeps long-term memory in a local Markdown knowledge graph and includes built-in surfaces like email, browser, notes, meeting transcription, and code mode.

A Noma Security research post detailing a prompt-injection flaw in GitHub Agentic Workflows, with attack flow, proof-of-concept evidence, and security recommendations.

A Pi extension that uses AI to generate and keep codebase documentation current, with commands for initial docs, incremental updates, and chat-based questions.

Local-first Python SDK for AI agents that compresses web pages before LLM use, flattens Shadow DOM, builds action maps, and extracts structured data from tables, forms, and lists.

A Claude Code skill that delegates coding, review, analysis, and research tasks to Google Antigravity CLI sub-agents so Claude can keep working while background jobs run.

A visual benchmark that asks AI coding agents to generate a single-file Three.js animation of a banana plant’s full life cycle, then compares the live results side by side.