Source-backed maps for builders choosing tools.https://arcyou.ai/https://arcyou.ai/teardowns/emilkowalski-skills-motion-design-system/https://arcyou.ai/teardowns/emilkowalski-skills-motion-design-system/A source-level teardown of how five motion-design skills separate vocabulary, principles, review, planning, and execution—and where two important workflow exceptions keep the architecture honest.Sun, 12 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/codexbar-provider-metering/https://arcyou.ai/teardowns/codexbar-provider-metering/CodexBar looks like a tiny macOS utility for AI coding limits. Read at v0.41.0, the real architecture is a curated provider catalog: compile-time provider IDs, descriptors, strategy pipelines, and separate app hooks that turn uneven vendor quota signals into one usage surface.Wed, 08 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/lazycodex-codex-harness/https://arcyou.ai/teardowns/lazycodex-codex-harness/LazyCodex is marketed as an agent harness for complex codebases. Read at v4.15.1, the source says something narrower and more useful: the root package is a small Codex install alias, the concrete product is the bundled omo plugin, and the deeper harness ownership points back to OmO.Mon, 06 Jul 2026 00:00:00 GMThttps://arcyou.ai/compare/vector-search-existence-models/https://arcyou.ai/compare/vector-search-existence-models/Vector search splits first by where it exists: Qdrant is a dedicated vector engine, pgvector is a PostgreSQL index access method, and LanceDB/Lance is an embedded file-backed stack. That operational home decides filtering, durability, consistency, and failure shape before benchmark tuning starts.Mon, 06 Jul 2026 00:00:00 GMThttps://arcyou.ai/compare/ai-coding-agent-context/https://arcyou.ai/compare/ai-coding-agent-context/The AI coding agents split by one design choice — how they get your code into the model's context. I read the source of three: Aider ranks a static graph, Continue embeds and retrieves, Cline gives the model tools and lets it read on demand. That single choice decides determinism, token cost, privacy, and how each behaves on a big repo.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/aider-repo-map/https://arcyou.ai/teardowns/aider-repo-map/Aider is pitched as AI that reads your whole codebase. Read at v0.86.3.dev, the repo map is a ranking problem, not an AI one: tree-sitter pulls the symbols, a PageRank over the reference graph ranks them, and a binary search packs the top ones into a token budget. No embeddings, no vector store, no network call.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/continue-codebase-indexing/https://arcyou.ai/teardowns/continue-codebase-indexing/Continue is the embedding-first counterpart to Aider. Read at v2.1.0, the answer to the question everyone actually asks — does my proprietary code get shipped to an embeddings API? — is: not by default. It embeds locally with a bundled all-MiniLM-L6-v2, stores vectors in a local LanceDB, and only sends code out if you configure a remote embeddings provider.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/lancedb-embedded-ivfpq/https://arcyou.ai/teardowns/lancedb-embedded-ivfpq/LanceDB is a library and a file format, not a server: connect() opens a local path or object-store URI in-process, and only URIs starting with the literal prefix `db` route to the Cloud HTTP client. Storage is the Lance columnar format with append-only manifest versioning, and the index family is IVF-first with PQ compression — not an HNSW graph. Read at lance v8.0.0 / lancedb v0.30.0.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/litellm-router/https://arcyou.ai/teardowns/litellm-router/LiteLLM is sold as a smart load balancer across your model deployments. Read at v1.92.0-dev.1, the default is a weighted coin flip: simple-shuffle picks a random healthy deployment, weighted by rpm/tpm if you set it. The intelligence — least-busy, latency, usage-based routing — is opt-in, and it works only because LiteLLM meters every key. On failure it runs a retry-cooldown-fallback ladder.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/ollama-model-scheduler/https://arcyou.ai/teardowns/ollama-model-scheduler/Everyone assumes Ollama estimates your model's memory and computes how many layers to put on the GPU. Read at v0.31.1, that's not what happens: Ollama is a scheduler that spawns an upstream llama.cpp llama-server, lets it auto-detect the GPU split by default, and reads the offloaded layer count back from its logs. Ollama's own memory math is a deliberately rough proxy used only to decide what fits and what to evict.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/pgvector-hnsw/https://arcyou.ai/teardowns/pgvector-hnsw/pgvector is the 'just use Postgres' answer to vector search, and the contrast with a dedicated engine like Qdrant is the home, not the algorithm. Both are HNSW; pgvector implements it as a Postgres index access method. Read at v0.8.4 — the graph lives in WAL-logged Postgres pages, a search is plain SQL, and filtering is Postgres's job, patched by a new iterative scan.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/qdrant-filtered-hnsw/https://arcyou.ai/teardowns/qdrant-filtered-hnsw/Adding a metadata filter is where naive vector search breaks — post-filtering wrecks recall, pre-filtering can't use the graph. Read at v1.18.2, Qdrant's answer is two moves: it estimates the filter's cardinality to choose between an exact scan and a graph search, and at build time it adds payload-aware links so a filtered subgraph stays connected — a fix it justifies with percolation theory.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/vllm-paged-attention/https://arcyou.ai/teardowns/vllm-paged-attention/vLLM's throughput comes from two linked ideas, read here at v0.24.0rc2 (the v1 engine). PagedAttention pages each request's KV cache into fixed 16-token blocks from a shared pool, so memory is non-contiguous, tightly packed, and shareable across identical prefixes. Continuous batching rebuilds the batch every forward step from a token budget, mixing prefills and decodes and preempting when blocks run out.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/compare/llm-gateway-camps/https://arcyou.ai/compare/llm-gateway-camps/The tools called LLM gateways split by what they route and who they're for. CLIProxyAPI pools your subscription logins. LiteLLM routes your API keys with metering and failover. Portkey is a stateless edge gateway driven by a declarative config. I read the source of all three, and the deciding axis is what state each one keeps.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/compare/local-inference-engines/https://arcyou.ai/compare/local-inference-engines/Self-hosting an open model splits into three camps by the layer you operate at. llama.cpp is the raw engine — a self-contained binary that loads GGUF and offloads layers to whatever hardware you have. Ollama is the friendly manager that wraps it. vLLM is the throughput server that replaces it. I read the source of all three to compare portability, convenience, and throughput.Thu, 02 Jul 2026 00:00:00 GMThttps://arcyou.ai/teardowns/cliproxyapi-account-scheduler/https://arcyou.ai/teardowns/cliproxyapi-account-scheduler/CLIProxyAPI is sold as an OpenAI-compatible proxy that round-robins across your Claude, ChatGPT/Codex, and Gemini subscriptions. Read the source and it's a reactive cooldown scheduler: it doesn't track your quota, it waits for a 429 — and only for Codex does it actually know when your limit resets.Wed, 01 Jul 2026 00:00:00 GMT