Guides
Practical guides on MCP, AI agent frameworks and AI developer tools. Each guide is based on the projects' own documentation and links to the tools discussed.
Archify review: Validation, delivery and offline diagrams
Testing Archify 3.2.0 with 18 CLI calls and 11 browser checks: invalid candidates, provenance, offline HTML, directed routes and a late browser-gate limitation.
Updated 2026-11-08
Anthropic Skills review Validation, packaging and PDF form limits
A pinned test of nineteen skill entries, archive filtering and real PDF forms. Text and checkboxes worked; a valid dropdown value was rejected despite a successful pypdf control.
Updated 2026-11-07
Claude Code Templates review What installation changes on disk
Real four-component installation from pinned CLI source, with byte checks and MCP merging. Tests exposed overwrite behavior, dry-run writes and a missing skill returning exit zero.
Updated 2026-11-07
ctx review Native history search, citations and incremental imports
Testing ctx 2.4.1 with artificial Claude Code and Codex transcripts: cross-provider search, exact readback, stable IDs, manual refresh and partial-rejection outcomes.
Updated 2026-11-07
FastMCP review: Validation, timeouts and tool scopes
Testing FastMCP 4.1.6 over real stdio and HTTP: input coercion, output contracts, error masking, timeout side effects and JWT tool permissions.
Updated 2026-11-07
Headroom review: Compression ratios and retrieval limits
Testing Headroom 0.43.1 with logs, typed JSON and real catalog data, including minification baselines, lossless fallback and original retrieval after MCP restarts.
Updated 2026-11-07
OpenKnowledge review MCP writes, search and restart recovery
Running published 0.89.3 against artificial Markdown to verify real MCP writes, edits, lexical search, ignore rules, file watching and persistence across server processes.
Updated 2026-11-07
Playwright MCP review: Forms, files and session isolation
Testing Playwright MCP 0.0.84 in real Chromium: form submissions, stale references, file bytes, isolated sessions, persistent storage and a response-body timeout.
Updated 2026-11-07
WebPerf Snippets review Performance budgets with real browser controls
Real Chromium tests of TTFB, CLS, INP, baseline regression and exit states, separating controlled local measurements from field-user Core Web Vitals.
Updated 2026-11-07
Xberg review: PDF tables, OCR and partial failures
Testing Xberg 1.3.9, the successor to Kreuzberg, on native and scanned PDFs: exact table cells, mixed pages, OCR numeric errors and batch failure handling.
Updated 2026-11-07
BoxLite review: Execution, persistence and network rules
Sixteen real BoxLite micro-VM checks cover shell results, file transfer, cross-process recovery, mount permissions, timeouts and reversible outbound allowlists.
Updated 2026-11-06
AIHawk review Job filtering and application state checks
Synthetic local tests of AIHawk search, deduplication, CV reading and attempt records, plus scripted post-submit outcomes and their limits.
Updated 2026-11-05
Awesome Copilot review What 457 validated skills establish
A pinned resource inventory and validator exercise separating file structure, plugin references, host compatibility and model effectiveness.
Updated 2026-11-05
Daily Stock Analysis review Local data and report checks
Synthetic tests of daily_stock_analysis database updates, isolated bindings, moving averages and permissive report parsing, with self-hosting requirements.
Updated 2026-11-05
Dashboard Icons review Service matching, variants and formats
Twelve local catalog checks test Dashboard Icons service names, aliases, theme variants, real asset paths and fuzzy limits using a pinned 3515-icon snapshot.
Updated 2026-11-05
dsh-Go review Encrypted sharing and link lifecycle
Source-level tests of dsh-Go conversation sharing cover decryption, deletion, expiry and quota failures, with clear limits on Android and remote-agent claims.
Updated 2026-11-05
Obsidian Second Brain review Crew logs and rule promotion
Local checks of shared Markdown logs, independent session reads, 24 concurrent writers and explicit lesson retention, including unread-history limits.
Updated 2026-11-05
Oh Story review Chapter checks and tracking consistency
A disposable Chinese-fiction project tests Oh Story length gates, explicit exceptions, state revisions and derived-file consistency without model generation.
Updated 2026-11-05
PI-Desktop review Session files and storage migration
Eleven local checks examine PI-Desktop file migration, lock exclusions, symlink handling and failure behavior without claiming a complete Electron or Rust migration.
Updated 2026-11-05
REA review What model headers and file hashes can prove
Twelve source-provider checks examine REA GGUF and safetensors metadata, tensor totals, header identity and refusal paths without loading a model.
Updated 2026-11-05
SkillSpector review Static findings need contextual review
A pinned 2.12.0 test of benign, unsafe and warning-only skill text, JSON and SARIF reports, findings exit codes and reviewed baseline suppression.
Updated 2026-11-05
Taste Skill 2.5.0 review From design rules to browser evidence
A pinned review of typography and CSS scripts and three-width overflow checks, with the limits of quick mode and opinionated design rules.
Updated 2026-11-05
Toonflow review Canvas connections and asset retention
Pinned local checks of media connections, asset cleanup candidates and Chinese script decoding, with deployment requirements and generation limits.
Updated 2026-11-05
Tyk review MCP configuration and Redis script checks
Pinned checks of Tyk MCP extension schemas and an isolated Redis sliding-log script, with deployment, licensing and runtime-testing boundaries.
Updated 2026-11-05
awesome-claude-code review Turning a directory into a useful shortlist
A pinned inventory audit of 263 records, 252 active links and six public destinations, covering categories, check dates, legacy entries and licensing boundaries.
Updated 2026-11-04
browser-harness review of browser control and error handling
Testing browser-harness 0.1.13 with local forms, uploads, retained state, tab switching and recovery, including an MCP result-format detail that hosts must handle.
Updated 2026-11-04
Claude Ads review Check the evidence before discussing optimization
A pinned local review of CSV normalization, invalid inputs, unknown findings and HTML reports, explaining disabled health scores and the limits of synthetic testing.
Updated 2026-11-04
Cognee review: choosing graph memory and verifying cross-session recall
A documentation-based analysis of permanent memory, session storage and local models, with a pilot plan covering updates, deletion and access isolation.
Updated 2026-11-04
datamodel-code-generator review Testing the contract after generation
A local 0.88.0 review of Pydantic and dataclass generation, covering invalid inputs, coercion, nullable defaults and repeatable output from a synthetic JSON Schema.
Updated 2026-11-04
.NET Skills review Reproducing two build-diagnostic workflows
A pinned MSBuild skills review using shared output paths, corrected offline compilation, four independent binlogs and text replay, with clear limits on host and model claims.
Updated 2026-11-04
GenAI_Agents review Reproducing tutorials before building an agent
We execute pinned trace-evaluation and human-approval tutorials, inspect rejection and replay behavior, and explain synthetic metrics, dependencies and the non-commercial license.
Updated 2026-11-04
Impeccable review: design skills, rule checks and a reproducible CLI test
A controlled test of Impeccable 4.8.0, with a practical distinction between design commands, deterministic detection, project context and Live Mode.
Updated 2026-11-04
MCP TypeScript SDK v2 review of integration and migration
A local test of MCP SDK 2.4.0 initialization, schema validation, tool errors, resource reads and process state, with practical v1 to v2 migration boundaries.
Updated 2026-11-04
Next AI Draw.io review for editable architecture diagrams
A reproducible check of Next AI Draw.io MCP 0.4.11 covering creation, atomic edits and drawio, PNG and SVG output, with browser dependencies and deployment tradeoffs.
Updated 2026-11-04
NocoBase 3 review From scaffolding to offline configuration checks
Fixed beta creator, template and CLI tests covering project generation, repeat initialization, database-dialect protection and YAML recovery, with clear Core and Studio boundaries.
Updated 2026-11-04
Parlant review: evaluating policies, tool checks and human handoff
A documentation-based review of Parlant 4.0.1 using an order-support pilot, with a multi-turn acceptance matrix and an explicit account of what remains untested.
Updated 2026-11-04
Choosing an Open-Source RAG and Knowledge-Base Platform: Five Questions to Ask First
How to pick between document-centric RAG engines, knowledge-base agent platforms and permission-aware company search, with notes on RAGFlow, MaxKB, PipesHub and the tools around them.
Updated 2026-10-08
Self-Hosted AI Assistants Compared: OpenClaw, nanobot, CowAgent and Letta
What a self-hosted personal AI assistant is, what to weigh before running one, and how OpenClaw, nanobot, CowAgent, Letta and the desktop-first alternatives differ.
Updated 2026-10-08
Web Tools for AI Agents: Browsers, Scrapers and Search, and When to Use Each
A task-based guide to the open-source tools that let AI agents operate websites, read pages, collect data at scale and search the web, covering Playwright MCP, Chrome DevTools MCP, Firecrawl, Bright Data, Apify, Scrapling and Brave Search.
Updated 2026-10-08
How to Choose an MCP Server: A Practical Evaluation Checklist
A checklist for judging MCP servers before you connect them to your AI tools — maintenance, permissions, transport, credentials, licensing and context cost — plus well-established picks by use case.
Updated 2026-10-07
Choosing a Multi-Agent Framework in 2026: CrewAI, AutoGen, MetaGPT, DeerFlow and More
How the most popular open-source multi-agent frameworks differ, which ones are actively developed, and a decision table for picking one based on what you are building.
Updated 2026-10-07
New on AgentIndex: 13 Tools Worth a Look (September–October 2026)
A curated look at the most interesting open-source AI agent tools added to AgentIndex between September 7 and October 7, 2026 — coding agent memory, document conversion, web scraping, security and more.
Updated 2026-10-07
Terminal AI Coding Agents Compared: Gemini CLI, Open Interpreter and the Tools Around Them
How open-source terminal coding agents differ on models, pricing, sandboxing and extensibility, plus the companion tools that make any coding agent more reliable.
Updated 2026-10-07
What Is MCP? A Practical Introduction to the Model Context Protocol
What the Model Context Protocol is, how hosts, clients and servers fit together, and how to connect your first MCP servers to Claude Code, Cursor and other AI tools safely.
Updated 2026-10-07