Posts

Coding agents lose context across repositories because a session is scoped to one repo while the system under investigation spans many. WCTX is a local-first MCP server that solves this by importing finished coding-agent sessions into a SQLite + FTS5 store, linking repositories with typed relations, and exposing seven tools that let a fresh session search prior evidence with git-based freshness verdicts. No cloud account, no embeddings, no transcript upload. ...

The Rapid-MLX DSH Provider is a native npm plugin for the DeepSeek Harness (dsh) that lets the agent read its model configuration straight from a running Rapid-MLX server’s /v1/models endpoint instead of hand-written settings.yaml. Instead of copying context windows, reasoning efforts, and max_model_len values by hand — and re-copying them every time you switch models — the provider serves those facts directly from Rapid-MLX’s JSON schema, keeps reasoning control truthful, and compacts the context at the real memory limit of your Apple Silicon machine. ...

ARC-Skill is a lightweight agent skill that lets an unmodified Claude Code agent finish all 25 ARC-AGI-3 games and all 183 levels at a perfect 100.00 RHAE score, using just 7,645 actions versus a median human’s 17,135. It works by enforcing a single rule: before the agent presses any button, it must write down exactly what that press will do to the grid, and the harness refuses to act until a prediction is recorded and graded. This article explains how that one rule unlocks frontier-level performance, how ARC-Skill compares to heavier harness systems, and what it teaches about agentic skill engineering. ...

The DeepSeek Harness iOS Simulator plugin is a live, interactive iOS simulator that runs inside a DeepSeek Harness (DSH) conversation — plus your real iPhone over USB — so your coding agent can see, tap, and verify the app it just changed. It ships 22 agent tools covering devices, screenshots, semantic UI navigation, build-and-run, SwiftUI preview hot reload, processes, and backtraces. This guide explains how it works, how to install it, and how it closes the verify gap that keeps coding agents from trusting their own Swift. ...

The DeepSeek Harness Agent Workflow plugin (dsh-plugin-agent-workflow) is a standalone, installable Web UI plugin that adds a dedicated “Workflow” tab to DeepSeek Harness, letting you orchestrate and inspect multi-step agent runs as a clear execution chain. It renders your real recorded Session events — model requests, model responses, and tool calls — in chronological order, split by user conversation turn, with token and cache statistics that reveal exactly how context is reused across steps. Because it is read-only and non-invasive, it never adds messages, prompts, or tools to your requests, making it a trustworthy observability layer for anyone running complex, multi-step agent workflows on DeepSeek Harness. ...

The DeepSeek Harness plugin hub is a decentralized, source-backed marketplace where every capability of the harness — models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI — is a swappable plugin. It grew from 0 to 7,740 plugins in under three weeks, making it one of the fastest-growing plugin ecosystems ever built. This guide explains how the hub works, how to install and publish plugins, and what to check before you trust one. ...

OpenSheet is an in-browser spreadsheet framework built specifically for AI agents, letting them read, query, and directly edit cells in CSV and Parquet files without sending your data to a cloud server. It runs on duckdb-wasm for local processing and evolved from the author’s earlier DataKit project. This review explains how it works, why spreadsheets are uniquely hard for LLMs, and how it compares to the growing field of spreadsheet agents. ...

If you have ever run two AI coding tools on the same repository, you have already met the problem PeerBridge MCP solves: left to themselves, Claude Code, Codex, Cursor, and Gemini edit the same files as if they were separate developers who never talk to each other. PeerBridge MCP is a local-first coordination server that gives those peers a shared, auditable state layer through the Model Context Protocol, so every read, write, and commit is tracked locally and drift is caught before it corrupts your codebase. In short, it turns a group of independent AI editors into a coordinated team with a written record of everything they touched. ...

ZhiShi is an open-source agent harness purpose-built for security research — a human-in-the-loop workbench for binary exploitation, penetration testing, whitebox code audit, and AI security — that layers a domain-specific research loop on top of the MIT-licensed @earendil-works/pi-agent-core engine. It uses a Tauri (Rust) desktop shell wrapping a TypeScript/Node core, and publishes unusual evidence-first proof of capability: 100% Pwnable.kr CTF completion, 98% Hacker101, and a fully reproduced exploit chain for CVE-2026-34621 (Adobe Acrobat Reader, CVSS 8.6). ...

Yes, you can run LLM commands on an ESP32. A 28.9M-parameter language model runs fully on-device on an ESP32-S3 at about 9.88 tokens per second, with 25M parameters stored in flash using Google’s Per-Layer Embeddings. However, models this small cannot follow instructions, answer questions, or write code — so true command execution requires either a more capable chip like the ESP32-P4 or a cloud-assisted setup. Why Run an LLM on a $6 Microcontroller The ESP32 family is the most popular microcontroller line in the maker and IoT world, and it costs as little as $6 to $10 per board. Running a language model on it means you get local, private, offline inference on hardware that costs less than a cup of coffee. There is no cloud bill, no network dependency, and no data leaving your device. ...