Skip to content
All tags

#mcp

77 posts

AI Agent GitHub Digest — 2026-09-05

mattpocock/skills gained 2,757 stars in a single day — the fastest-growing repo on GitHub today. Anthropic's own anthropics/skills and the open-source coding agent anomalyco/opencode are trending alongside it. Meanwhile MCP server reverify ran a benchmark on 71 real Windows system files and found AI has a 97% error rate reverse-engineering binaries from memory — deterministic tools caught every single one. On the framework side, pydantic-ai, agno, and haystack all shipped routine patches today, nothing major.

AI Agent GitHub Digest — 2026-09-02

openclaw/openclaw, a self-hosted personal assistant, has climbed to 388k stars by wiring WhatsApp, Telegram, Slack and other chat channels into one Gateway. The same week, NVIDIA shipped SkillSpector, which scans Claude Code, Codex, and MCP skills for 71 vulnerability patterns — research it cites found 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent. Also today: stablyai/orca turns parallel multi-agent coding into a full IDE, and VectifyAI/PageIndex challenges the assumption that RAG needs a vector database with a reasoning-based tree index. claude-code v2.1.257 adds a Containment Escape security rule, and agno v3.0.5 stops swallowing embedding failures silently and starts reporting them honestly.

AI Agent GitHub Digest — 2026-09-01

HKUDS/nanobot hit 47.5k stars in half a year, demonstrating the 'small core + multi-channel + long-term memory' formula for a self-hosted personal agent; zhayujie/CowAgent (formerly chatgpt-on-wechat) reinvents an old chatbot wrapper as a full Agent Harness with a three-tier memory architecture and a nightly 'Deep Dream' distillation pass; conductor-oss/conductor wires a durable-execution graph engine to native MCP tool calls, letting an agent's loop survive a crash or a weeks-long human approval wait; mksglu/context-mode goes straight at the pain point of MCP tool calls flooding the context window, and hit #1 on Hacker News. agno v3.0.4 is the only framework release that clears the bar — it flips KnowledgeManagementTools' ingest_path to opt-in by default to close a security gap.

AI Agent GitHub Digest — 2026-08-31

can1357/oh-my-pi forked the well-known coding agent 'Pi' and, by obsessing over tool-call formats, pushed Grok Code Fast 1's task success rate from 6.7% to 68.3%; K-Dense-AI/scientific-agent-skills opens 163 research skills to any agent that supports the Agent Skills standard; addyosmani/agent-skills packages a senior engineer's six-stage workflow into a skill set and hit 90k stars in a week; THU-MAIC/OpenMAIC v1.0.0 adds a conversational Pro workbench, landing multi-agent orchestration in the concrete vertical of course content production. On the framework side, agno v3.0.2 is the one release that clears the bar: it publishes Agents/Teams/Workflows as named MCP tools and ships several breaking changes along the way.

Learning Design from Mature Coding Agents (30): MCP Integration — the Standard Socket for Tool Ecosystems

An MCP client must handle transports, tool refresh, approvals, and credential boundaries together. looplane now supports allowlisted stdio, Streamable HTTP/SSE, tools/resources/prompts, tools/list_changed, OAuth metadata/PKCE, and a 0600 credential store. A real authorization-server E2E and MCP-specific confirmation UX remain open.

Looplane Native MCP: transport, authorization, and approval boundaries

Looplane loads project MCP servers only through an explicit allowlist, projects stdio or Streamable HTTP capabilities into the existing ToolExecutor, and preserves hooks, approvals, timeouts, and cleanup.

How AI Agent Search Infrastructure Is Changing: Keenable, Independent Indexes, and NEEDLE

Keenable.ai positions itself as search infrastructure for AI agents: a 100B+ document index, Search/Fetch APIs, MCP/CLI entry points, 100K free monthly requests, and keyless public endpoints. It is worth tracking, but the 100B+ index, latency, and quality claims are still mostly company-provided; NEEDLE is open, but needs external reruns and human review.

Governance Deep Dive: Policies, Omnibox, Spend Controls and Credential Brokering

Omnigent moves governance off prompts into a Server-side Policy engine: Python functions returning allow/deny/ask, a three-layer stack with cost budgets and tool caps, plus Omnibox OS-native isolation via bwrap/seatbelt and egress credential brokering — compared with five peer governance stacks.

Same Name, Different Layer: meta-harness, ACP, HarnessAgent and Flue

meta-harness means two things: Databricks' control plane and Stanford's outer-loop optimizer. This post uses a four-layer model (MCP/ACP/Runtime/meta-harness) to place Omnigent, Zed ACP, Vercel HarnessAgent and Cloudflare Flue.

Managing Multiple Agents Together: Omnigent's Meta-Harness, Policies, and Cross-Device Sessions

Databricks' open-source Omnigent wraps Claude Code, Codex, Cursor, Pi and custom agents in a Runner/Server + Omnibox sandbox, adding three-layer Policies and shareable persisted Sessions so you can swap models and harnesses with one-line changes — 9.3k stars, still alpha.

Security Alert|NVIDIA NemoClaw: One Website Visit Can Poison Your Local AI Model (CVE-2026-65105)

NVIDIA NemoClaw (the official tool for deploying OpenClaw agents) binds Ollama to 0.0.0.0 so sandbox containers can reach the local inference server — but this disables Ollama's Host header check that blocks DNS rebinding. An attacker only needs the developer to visit a malicious webpage to gain full unauthenticated access to the Ollama API, then use /api/create to modify the model's Go template and permanently embed malicious instructions — a technique that survives even the agent's own system prompt sent with every call. Mitigations: bind Ollama to loopback only, put an auth proxy in front, enforce a Host header allowlist, and don't rely on sandbox isolation alone.

Agentic / Reasoning RAG: From Search-R1's RL Multi-Turn Search to Deep Research and MCP's Reasoning × Retrieval Paradigm

In 2025 RAG stopped being 'retrieve once, generate once.' Search-R1 trains models to search autonomously in multiple turns with RL, REX-RAG/AlignRAG add policy and alignment branches, OpenAI Deep Research productizes the loop, and MCP generalizes retrieval into unified tool invocation. This post unpacks the design philosophy, trade-offs against ten generations, and when to adopt the new paradigm.

Security Alert|Omnigent Agent Bundle Upload Vulnerabilities — Three Critical CVEs Let Authenticated Users Own the Runner Host

Omnigent is an open-source meta-harness that unifies management of Claude Code, Codex, Cursor, and other coding agents. On 8/21, three CVEs were disclosed: CVE-2026-62674 (CVSS 9.0, upload a forged shared agent bundle embedding a stdio MCP server to achieve runner RCE), CVE-2026-62675 (uploaded bundle declares a Python callable tool that the runner executes directly), and CVE-2026-62677 (unvalidated os_env.cwd in the bundle lets the agent read/write the entire runner filesystem and leak credentials from environment variables). All three share the same root cause: the agent bundle upload path over-trusts tenant-supplied content. Patched in 0.3.0 — any multi-user or self-hosted Omnigent deployment should upgrade immediately.

tech deep-dive

Agent Platform Deep Dive (Part 4) — Provider Router & MCP: Multi-Provider Routing, Fallback Chains, and an OpenAI-Compatible Proxy

The Provider Router is Agent Platform's model and tool gateway: it unifies 30+ providers, MCP tool discovery, step-local permission control, fallback chains with RRF fusion, and an OpenAI-compatible Proxy that existing SDKs can use without code changes. It is configuration-driven rather than hard-coded, with provider-health-aware routing.

tech deep-dive

Groundlane Series Part 1: Why AI Agents Need a Controlled Web Access Layer

Groundlane is an open-source TypeScript remote MCP server (v0.1.0) giving AI agents web_search, web_fetch, and web_extract through a single stable contract, with auth, provider routing, and resource limits kept at the operator boundary.

tech deep-dive

Groundlane Series Part 2: Actual Calls, Response Structures, and Error Boundaries for the Three MCP Tools

Hands-on parameter choices and response structures for web_search (ten adapters, RRF merge, dual-provider default), web_fetch (format/render strategies, finalUrl provenance), and web_extract (CSS selector determinism, no implicit LLM step), with verifiable error boundaries.

tech deep-dive

Groundlane Series Part 3: Comparing with Traditional Approaches — WebFetch, stealth_fetch, puppeteer, and requests

A four-dimension comparison (determinism, replaceability, identity boundary, operational cost) between Groundlane's controlled remote MCP contract and traditional local approaches (WebFetch, stealth_fetch, puppeteer, requests), with verifiable scenario recommendations.

tech deep-dive

Groundlane Series Part 4: In-Site Application — Verified Workflow with Existing MCP Tools and Usage-Mode Rules

Based on the in-site groundlane skill (mcp__groundlane__*) and usage-modes rules, this part describes reproducible steps for reference verification and digest data collection — without assuming unimplemented features or using deprecated stealth_fetch.

tech deep-dive

Groundlane Series Part 5: Pitfalls and Best Practices — timeout, selector, render mode, version-change risk, and security boundaries

A reproducible checklist of the most common operational pitfalls: truncated results from fixed caps, selector errors tied to DOM stability, render-mode cost/determinism tradeoffs, version-change verification (v0.1.0 preview), and the non-negotiable security boundaries (URL policy, auth, concurrency, budget).

Giving an Agent Access to Logged-In Websites: Sessions, Permissions, and Automation Boundaries

Authenticated browser state is not a convenience setting; it is a credential that can impersonate its owner. Use a dedicated low-privilege account and isolated profile, separate reading from reversible writes and high-risk transactions, and leave MFA plus final submission to a human.

ai deep-dive

Flowise Deep Dive: From Assistant, Chatflow, and Agentflow to an EOL Migration Decision

Flowise uses Assistant, Chatflow, and Agentflow to cover simple assistants, single-agent systems, and multi-agent orchestration; however, its repository was archived in August 2026 and official EOL is scheduled for August 31, so new projects should not adopt it without a maintained fork and migration plan.

ai deep-dive

OpenViking: Agent Memory as a Virtual Filesystem

Volcano Engine's open-source OpenViking stores agent memory, knowledge, and skills as a viking:// virtual filesystem — browsable with ls, tree, and find. Three-tier loading (L0/L1/L2) averages just 550 tokens per retrieval, boosting LoCoMo memory accuracy from 24–57% to 80–83%.

Agent Plugins 1.0: OpenAI, Google, and AWS Unite to Standardize AI Agent Extensions

Agent Plugins 1.0 is a packaging format that bundles Agent Skills (markdown instructions) and MCP server configs into a single directory, loadable by ChatGPT, Cursor, GitHub Copilot, Kiro, and VS Code. It's not a new protocol — it's the wrapper above protocols. Vercel initiated it, OpenAI/AWS/Microsoft/Cursor co-authored it, and Google joined on launch day. Anthropic isn't on the governance board, but MCP is a core primitive of the spec.

Composio: Who Holds Every User's Token When Your Agent Connects a Hundred SaaS Apps

This site covers MCP thoroughly but has never written about the layer underneath it: when your agent acts for ten thousand end users reading their own Gmail, whose database holds those refresh tokens, who rotates them, who revokes them. Composio is currently the most complete answer — MIT-licensed SDKs, a commercial hosted execution and OAuth layer. It claims 1,000+ toolkits; the managed-auth page actually lists 121 with a Composio OAuth app and 96 that require your own credentials. New pricing effective 2026-08-15: 100K free tool calls, $29/mo Pro. This post takes the authorization model down to an operational level and draws the line between wiring up MCP servers yourself and buying an integration platform.

Exa: Neural Search Built for Agents, Not People

Exa turns every indexed web page into an embedding and retrieves by vector similarity instead of keyword matching. Official pricing as checked on 2026-08-21: $7 / 1k requests for /search (first 10 results included), $1 / 1k pages for /contents, $12–15 / 1k for the deep tiers, with $20 in free credits for new accounts. This blog's CLAUDE.md puts Exa first among cloud fetch tools, 16 of its 38 skills reference it directly, and only four existing posts mention it in passing — with zero dedicated posts. This is that post.

Microsoft Agent Framework: After the Merge, Who Does the Name AutoGen Point To?

Microsoft merged Semantic Kernel and its own AutoGen into Microsoft Agent Framework, which hit 1.0 GA on 2026-04-02 for .NET and Python (Go is still public preview). The absorbed autogen-agentchat has not shipped since 2025-09-30. But AG2, the fork on the original authors' side, never merged — it shipped 1.0.2 six days ago, and `pip install autogen` gets you AG2, not Microsoft. This post covers MAF's abstractions, the migration clock, and how to read the tangle of names.

Build Your Own Search Backend: SearXNG + Crawl4AI, From Zero to Claude Code

Three components, one job each: SearXNG finds, Crawl4AI reads, and a thin layer of your own code glues them together. Three defaults will stop you cold — `formats` only emits HTML, `secret_key` ships as the literal string `ultrasecretkey`, and turning on the limiter blocks your own code. Also, the official install path changed in March 2026, so most tutorials online point at a repository that is now archived.

Security Alert | Splunk MCP Server Hit with CVSS 9.1 Deserialization RCE, AI Toolkit Also Affected

On 2026/8/19 Splunk published SVD-2026-0808, patching 17 vulnerabilities across the Cisco Talos add-on, AI Toolkit, Connect for Kafka, MCP Server app, and On-Call. The most severe, CVE-2026-76404 (CVSS 9.1), is in the Splunk MCP Server app's credential management component — unserialized stored data without type validation lets admin-role users execute arbitrary OS commands. CVE-2026-76395 (CVSS 8.8) in AI Toolkit triggers similar RCE when loading model files containing pickle payloads. No in-the-wild exploitation observed. Mitigation: upgrade MCP Server app to 1.2.1 and AI Toolkit to 6.0.1 immediately; disable the app if you cannot upgrade right away.

shadcn Registries and MCP: The Third Way to Distribute Components

Component distribution used to offer two roads: npm packages (black-box dependencies) or manual copy-paste. The shadcn registry standardizes a third — components described as JSON with embedded source and dependencies, installed by CLI straight into your repo as your own code. Anyone can host a registry (AI Elements is one), and the official MCP server lets AI agents browse and install components directly.

WebMCP: Letting a Web Page Hand Its Own Functions to an Agent

WebMCP lets a page register its own functions as agent-callable tools via document.modelContext.registerTool(), replacing the agent's guess-the-button DOM scraping. Chrome opened an origin trial in 149 and estimates stable in 157; Edge followed in 150. But WebKit has formally opposed it ('an agent acting on a user's behalf is, in effect, assistive technology... the site should not single it out for different treatment') and Mozilla filed neutral. This post covers both APIs, where the security gates sit, and whether to invest now with one and a half engines behind it.

GitHub Copilot CLI: An Agent That Runs on GitHub the Platform

Copilot CLI went GA on 2026-02-25 and is included in every Copilot plan, Free included. Its differentiator isn't the agent — it's the GitHub integration: a built-in GitHub MCP server that works on issues and PRs, org policies inherited automatically, and an `&` prefix that hands work to the cloud coding agent. Billing runs on GitHub AI Credits (1 credit = $0.01): Pro $10/mo includes $15, Pro+ $39 includes $70, Max $100 includes $200.

Claude Certified Architect Foundations Exam Complete Guide

A complete study guide for Claude's official architect certification (CCAR-F): five domains weighted 27/18/20/20/15, four scenarios drawn from six, common anti-patterns, and hands-on preparation. Official specs are 60 items / 120 minutes / $125 / 12-month validity / 720 to pass; registration is limited to Claude Partner Network members, and on-time renewal is free and non-proctored.

Claude Certified Developer (CCDV-F): A Third of It Is Ordinary Software Engineering

CCDV-F is the engineer's exam among Anthropic's four certifications. The official blueprint has eight domains, and the heaviest — Applications and Integration at 33.1% — is led by Claude Application Design (8.6%) and Software Engineering Foundations (7.4%), meaning a third of the exam is API mechanics and ordinary software engineering. The counterintuitive part: Claude Code is only 3.1% and Eval only 2.6%, while the sibling Architect exam gives Claude Code 20%. Official specs: $125, 53 items, 120 minutes, pass at 720, valid 12 months, registration limited to Claude Partner Network organizations.

The Hermes Agent Tool Layer: What Happens When 3,300 MCP Tools Won't Fit in Context

Attach enough MCP servers and the tool schemas alone eat your context — upstream's extreme example is Cloudflare's ~3,300 tools, whose names alone run about 32K tokens. Hermes answers with Tool Search: MCP and non-core plugin tools collapse into three bridge tools and schemas load on demand, while core tools never defer. Separately, plugins are disabled by default and only run when named in `plugins.enabled`.

Multi-Agent Architecture Across Five Exams: The Shared Core and What Doesn't Transfer

Microsoft AI-500, AB-620, AB-100, NVIDIA NCP-AAI, and Claude CCAR-F all test multi-agent architecture, and they overlap on seven things: orchestration topologies, A2A and MCP, per-agent identity boundaries, three-layer memory, observability and agent replay, human-in-the-loop, and guardrails at four intervention points. But four vendors use four vocabularies for the same ideas, and each exam has objectives that don't transfer — Microsoft names four context-window failure modes nobody else names, 7% of NVIDIA's is locked to NeMo and NIM, and Claude tests SDK-level details like stop_reason. One correction along the way: Google PMLE's wall-to-wall 'Agent Platform' is a Vertex AI rename, not a multi-agent domain.

Security Alert | Flowise Custom MCP Node Command Injection — Fourth RCE CVE in One Year (CVE-2026-73601)

Security firm elttam discovered that when Flowise's Custom MCP node runs with CUSTOM_MCP_PROTOCOL=stdio (the default), authenticated users can abuse PYTHONWARNINGS/BROWSER environment variables or exploit the StdioClientTransport's root cwd to bypass existing command and path validation, achieving arbitrary command execution on the host. Rated CVSS v4.0 9.0 Critical, patched in 3.1.3 (CVE-2026-73601). This is the fourth publicly reported RCE against the same Custom MCP feature within one year, highlighting that a 'whitelist commands, blacklist arguments' validation architecture is virtually guaranteed to be bypassed when users can define their own stdio MCP servers. Key mitigations: upgrade, switch CUSTOM_MCP_PROTOCOL to sse, and stop relying on deny-list validation for env/command — an approach that never eliminates the attack surface itself.

CS146S Week 9: One Person Wiring Up MCP Is Fine; Three Hundred Need a Gate

How an individual connects tools is a preference; how an organization does it is governance — who can touch what data, where keys live, whose budget it lands on. Anthropic's published record of ten internal teams contains a good indicator: security engineering accounts for 50% of all custom slash commands in the entire monorepo. Adoption doesn't spread evenly; it takes off first in teams that already build their own tools.

CS146S Week 2: Context Engineering, RePPIT, and MCP's 98.7% Cut

Fall 2026 compresses a full week of prompting into one bullet here and adds RePPIT (Research, Propose, Plan, Implement, Test) and MCP. Two RePPIT rules are worth stealing outright: always ask for exactly two proposals, and never let the instance that wrote the code review it. On the MCP side, Anthropic measured turning tools into code calls dropping 150,000 tokens to 2,000.

Security: Prompt Injection Can Only Be Contained in the Harness

In November 2025 three frontier labs jointly broke all 12 previously proposed prompt-injection defenses. EchoLeak's payload passed Microsoft's own dedicated classifier. So the goal is not blocking every attack — it is surviving the ones that land, and that is harness work.

Drawing the Lines: Agent, Workflow, RAG, and MCP

The line between workflow and agent is who decides the steps — the developer at design time, or the model at run time. By that definition most LLM systems in production today are workflows. Plus a usable test for choosing between RAG and an agent.

The Protocol Layer: MCP, A2A, ACP, Skills

MCP governs agent-to-tool, A2A governs agent-to-agent, Skills govern reusable knowledge. The test is whether the data changes: if it changes between calls you need MCP; if it's stable enough to write down, a skill file is simpler and has no runtime that can fail on its own.

tech deep-dive

Three Routes to Hand-Drawn SVG Icons: A ~88k Free Library, a Generator That Bends Lucide, and the License Page Nobody Reads

Koboyo claims close to 90,000 free hand-drawn SVG icons (the count oscillates: 92,967 → 87,954 → 90,150), but its sitemap only lists about 17,930 icon pages, and its license page explicitly forbids building an icon library or canvas app with them. There are actually three routes to a hand-drawn look: collect a library, bend existing geometry programmatically (sketchyicons turns every straight run in Lucide into a quadratic Bézier, seeded by icon name for byte-for-byte reproducibility), or generate with AI. This piece compares seven libraries on scale and license, unpacks the algorithms behind sketchyicons and tldraw, and surveys the icon search tools now shipping MCP servers.

ai guide

Which AI Courses to Take in 2026: From AI-Curious to Vibe Coding to Production

Every official course platform from OpenAI, Anthropic, and Google, plus Stanford CS146S/CS336, Elements of AI, Hugging Face, MIT 6.S191 and more — scraped page by page, then re-sorted into four tiers: AI-curious, vibe coding, shipping to production, and how models actually work. Also covers self-study repos still being updated in 2026 and browser-based platforms that need no local setup, filtered by last-commit date rather than star count. The conclusion: nearly all of it is free. What is scarce is not courses, it is the judgment to pick one. And tier four will not fix your tier three problem.

Choosing a Browser MCP: CDP, Playwright MCP, or Puppeteer MCP?

It's really a two-way choice now: @playwright/mcp (cross-browser, accessibility tree, token-cheap) versus chrome-devtools-mcp (Chrome's official server, performance and memory diagnostics). @modelcontextprotocol/server-puppeteer has been archived and is no longer a candidate. The dividing line is no longer abstraction level — it's 'drive the page' versus 'diagnose Chrome'.

Chrome DevTools MCP: The MCP Server Wired Directly to CDP

chrome-devtools-mcp, maintained by the Chrome team, packages DevTools capability as an MCP server: performance traces and insights, Lighthouse audits, heap snapshots, extension management — none of which @playwright/mcp exposes. It runs on Puppeteer, so interactions auto-wait; the costs are Chrome-only support and usage statistics reported to Google by default.

@playwright/mcp: Microsoft's Official Browser Automation MCP Server

@playwright/mcp defaults to an accessibility tree (browser_snapshot) instead of screenshots, cutting token consumption sharply. Combined with Playwright's native auto-wait it's a sensible starting point for AI agents doing web automation — but note it now runs headed by default, keeps a persistent profile by default, and gates advanced tool groups behind --caps.

@modelcontextprotocol/server-puppeteer: The Official Puppeteer MCP Server

server-puppeteer is the Puppeteer wrapper in the official MCP servers monorepo — seven lean tools built around screenshots and evaluate. It has since been archived (moved to servers-archived, no longer published), so it is not a choice for new projects; if you want Puppeteer lineage in an MCP server today, look at the Chrome team's chrome-devtools-mcp.

ai deep-dive

How to Pick the Right Tool from Hundreds: The Collapse Curve of Tool Selection and Engineering Solutions

As tools scale up, selection accuracy doesn't degrade gracefully — it collapses: 4 to 51 tools drops from 43% to 2%, 10 to 100+ drops from 78% to 13.62%. The root fix is to stop stuffing everything in at once — Anthropic's Tool Search Tool uses defer loading plus retrieval to cut 85% of tokens, pushing Opus 4.5 accuracy from 79.5% to 88.1%. Description quality has conditional payoff: negligible in simple scenarios, but correctness jumps from 44% to 50% in multi-tool chaining.

tech deep-dive

Bumblebee: A Design Teardown of Perplexity's Read-Only Supply Chain Endpoint Scanner

A Go read-only scanner open-sourced by Perplexity in May 2026 (v0.1.1, zero non-stdlib dependencies). It inventories npm/PyPI/Go/RubyGems/Composer/MCP/editor and browser extensions into NDJSON, matches against a custom exposure catalog, and answers the question 'which machines in my fleet are currently affected' the moment a supply chain incident hits. It deliberately never invokes any package manager and is not an EDR.

ai deep-dive

A2UI (Agent-to-User Interface): Google's Open Protocol for Agents to Ship UI as Data

A2UI is an agent generative UI protocol open-sourced by Google on 2025-12-15: agents send declarative JSON describing UI intent, and clients render it natively using their own component catalog whitelist, layered on top of A2A. It launched at format v0.8 and iterated to v0.9 within three months.

ai deep-dive

CodeGraph: Local Code Knowledge Graph, and the Truth About 'Walking the Graph to Save Money'

CodeGraph uses tree-sitter to extract a codebase into a local SQLite/FTS5 knowledge graph, letting AI coding agents query the graph instead of scanning files. The official end-to-end benchmark (7 repos, median of 4 runs) averages 35% cost savings and 70% fewer tool calls -- but only if the agent actually walks the graph. Delegating exploration to a file-reading subagent that ignores CodeGraph turns it into pure overhead.

Midscene.js: Betting on Pure Vision for Cross-Platform UI Automation

An MIT-licensed open-source UI automation framework from ByteDance. UI actions rely solely on feeding screenshots to a vision-language model, with no DOM parsing. A single JS API works across Web / Android / iOS / desktop. The trade-offs: each step is slower and more token-expensive, and everything hinges on the model's grounding ability. Note that Midscene retired MCP after 1.9.8 in favour of Skills + CLI.

ai deep-dive

Open Design: The Open-Source Claude Design Alternative Forked in 11 Days

Anthropic shipped Claude Design on 2026-04-17. On 4-28, nexu-io/open-design went public -- same artifact-first loop, Apache-2.0, runs on the 16 coding-agent CLIs you already have. Two weeks from 0.1 to 0.7, 40k+ stars. A paradigm shift that flattens AI design tools from vertical SaaS into a skill bundle.

ai deep-dive

Using AI Agents to Operate Video Generation Tools: A HyperFrames, HeyGen, and Runway Integration Guide

AI agents can operate video generation tools through three approaches — Skills, MCP Connectors, and direct APIs. Choosing the right integration method matters more than choosing the right tool.

ai deep-dive

Code Mode: Moving Tool Definitions from Context into Code

Stop stuffing all your tool descriptions into context at session start. Let the model write code, have the runtime execute it, and let tool definitions enter context only at the import line — Anthropic's GDrive→Salesforce example dropped from ~150K tokens to 2K, and Cloudflare's 2,500-endpoint schema shrank from 1.17M to 1K.

ai deep-dive

Claude for Financial Services: Dissecting Anthropic's Multi-Agent Reference Implementation

Anthropic open-sourced 12 financial-industry Agents and 11 MCP connectors. The real takeaway isn't the Agents themselves but the layered design of 'one prompt, two runtimes' and 'pure-file extensibility.'

Search MCP Tools for AI Agents: What to Do When WebFetch / WebSearch Gets Blocked

When using AI agents like Claude Code or Cursor, built-in WebFetch / WebSearch often gets blocked by Cloudflare, geo-restrictions, or rate limits. Connecting a search MCP server is the most direct fix. This post compares the options actually available in 2026.

goose: Open-Source, Cross-Platform, LLM-Agnostic Local AI Agent

goose is an open-source AI Agent maintained by the Linux Foundation's AAIF, supporting 15+ LLM providers and 70+ MCP extensions, built with Rust as a Desktop App + CLI + API. It positions itself as a vendor-neutral, self-hostable alternative to Claude Code.

AEO / GEO Tool Landscape: Input, Traffic, and Output Layers — From isitagentready to aeo-radar to Profound

AEO/GEO tools aren't a single category — they span three distinct layers: the input layer (is your website ready for AI to read), the traffic layer (how much are AI bots actually crawling), and the output layer (how is your brand mentioned in AI answers). This post maps out all three layers, from open-source self-hosted options to commercial SaaS.

Agentic Engineering: Making AI Agents Collaborate Like a Real Engineering Team

Agentic Engineering isn't about making AI write code faster — it's about making software move through the entire delivery pipeline faster, by using multi-agent collaboration to compress cross-team coordination friction.

ai guide

MCP vs CLI vs API: The Real Boundaries of Agent Tool Interfaces

MCP is not going away, but its effective scope is narrower than most people think. For local development, CLI and raw API almost always beat MCP. MCP's truly irreplaceable niche is the narrow gap of 'cross-agent shared local tool layer.'

ai guide

Graphify: Turn Code and Documents into a Queryable Knowledge Graph

Graphify uses tree-sitter AST to extract code structure, then applies LLM semantic analysis to documents and images, compressing an entire project into a queryable knowledge graph. It claims to save 71.5x tokens per query compared to reading raw files.

Claw Code: An Open-Source CLI Agent That Rewrites Claude Code in Rust

Claw Code is a from-scratch Rust rewrite of the Claude Code CLI, featuring 48K lines of code, 40 tools, and MIT licensing. Most remarkably, the entire project was built by multiple AI agents collaborating over just 5 days, surpassing 170K GitHub stars within a week of launch.

ai project

OpenHarness: A Fully Open-Source Agent Harness Framework

An open-source Agent Harness framework from HKUDS (HKU Data Science Lab) that implements tool calling, skill loading, memory, permissions, and multi-agent collaboration as complete infrastructure, supporting Anthropic / OpenAI / GitHub Copilot API formats.

tech guide

code-review-graph: Using a Knowledge Graph to Cut AI Code Review Token Usage by 8x

code-review-graph uses Tree-sitter to parse your codebase and build a persistent knowledge graph, tracks the blast radius of changes, and feeds only truly relevant context to the AI — claiming an average 8.2x reduction in token usage.

The Complete Guide to Agent CLIs: Design Logic, Tool Comparison, and Best Practices

Agent CLIs are not smarter autocomplete tools -- they are AI agents that can read your codebase, execute multi-step tasks, and operate in real environments. Claude Code, Codex CLI, Gemini CLI, OpenCode, Aider, Pi, Kiro, Amp, Cursor CLI... the tools keep multiplying, but they all share a common set of design principles -- understanding these principles is how you actually get good at using them.

AI-Ready Content: The Complete Guide to Making Your Website an AI-Readable Data Source

In 2025-2026, websites need to be readable not just by humans but by AI. From llms.txt and Schema Markup to GEO and RAG ingestion pipelines, this post maps out the complete technical landscape for turning your website into an AI-consumable data source.

OpenClaw Tools, Part 4: When the Catalog Outgrows the Prompt — Code Mode, Tool Search, and MCP

When the tool catalog no longer fits in the prompt, OpenClaw offers two answers: Code Mode shows the model only exec and wait and has it write small programs against a hidden catalog, while Tool Search keeps structured search/describe/call controls. Neither bypasses tool policy.

Complete Guide to Bypassing Cloudflare Anti-Bot for AI Agents: From Debugging to Building an MCP Server

Standard Playwright gets blocked by Cloudflare. Both playwright-extra + stealth and nodriver can bypass it. The final step is wrapping the solution into an MCP server so AI agents can use it automatically.

Claude Code Channels: External Events, Reply Tools, and Sender Gating

Channels are a special kind of MCP server that push CI failures, monitoring alerts, and Telegram messages directly into a running Claude Code session — and Claude can answer back through the same channel via a reply tool. This post breaks down the channel contract, two-way replies, security gates, and install requirements.

How Claude Code Sees Your Browser: Chrome Integration, Console Debugging, and Form Automation

Claude Code gains browser control through the Claude in Chrome extension: read console logs and DOM state, click, type, upload files, record GIFs, and operate sites you're already signed into. The official prerequisites list Chrome, Edge, and Chromium-based browsers such as Brave, Arc, Vivaldi, and Opera, but WSL is not supported.

How Claude Code connects to external tools: MCP scopes, transports, and auth

Claude Code connects to external tools via MCP (Model Context Protocol), with manual configuration split across three scopes: team-shared .mcp.json, personal local/user entries in ~/.claude.json, and enterprise managed config — not settings.json. This post covers claude mcp add/login flows, the transport landscape (SSE is deprecated), and tool search lazy loading.

ai guide

MCP (Model Context Protocol): The Standardized Protocol for AI Agent Tool Invocation

Every AI tool has its own calling format, making integration costly. MCP (Model Context Protocol) is an open standard proposed by Anthropic that unifies the communication protocol between AI Agents and external tools/data sources, enabling tools to be reused across Agents.

tech guide

Turning a Scraper Script into an MCP Server for Claude to Use Directly

Wrap a local Python script into an MCP Server using FastMCP so Claude Code can call it directly — no more manually running pipelines.

tech debug

MCP Tool Returns 1M Characters: The Token Explosion in search_local_jobs

The MCP tool was returning a description field that caused 1,033 job listings to exceed the token limit. The fix: exclude description by default and add pagination.

ai deep-dive

Complete Guide to AI Agent Architecture Patterns: From Three Pillars to Multi-Agent Systematic Navigation

AI Agent is not a single technology -- it is an entire architecture system. This article is a systematic navigation: starting from the Agent Three Pillars (Context/Cognition/Action), through the three-stage evolution of AI engineering (Prompt -> Context -> Harness), to eight Multi-Agent design patterns and production-grade Harness infrastructure. Each topic links to a dedicated deep-dive article.

ai guide

The Three Core Pillars of AI Agents: Context, Cognition, Action

An AI agent is not a black box — it is built from three layers: what it knows (Context), how it thinks (Cognition), and what it can do (Action). Understanding these three layers is the key to grasping why agents are sometimes brilliant and sometimes go off the rails, and how to design a truly effective agent system.