Production-tested skills for AI agents. Every skill is security-scanned, tier-rated, and verified. Browse by ecosystem or category below.
Claude Code has a subconscious. Codex CLI has nothing. Gemini CLI has nothing. Letta Code has actual, version-controlled, subagent-maintained memory — and the sleep-time compute idea from their April 2025 paper is now productized as background dream agents.
On June 30, 2026, Anthropic shipped Claude Sonnet 5 and quietly closed most of the gap to Opus 4.8 at one-third the price. SWE-bench Pro 63.2%, OSWorld 81.2%, HLE 57.4%. The mid-tier is now the new default for production agents.
Tired of waiting 15 seconds for Ollama to reload llama3 every time you step away? One tiny env var kills that cold-start penalty for good. Here's the line, the gotchas, and the per-request override.
Most agent frameworks are overengineered abstractions that hide bugs, lock you into their API surface, and make production agents harder to debug. A 100-line vanilla Python tool-calling loop will beat them for 90% of real work — here is the case for skipping the framework.
LanceDB is an open-source, embedded multimodal vector database built on the Lance columnar format — Apache 2.0, Rust core, used by Netflix and AWS at production scale. Most RAG and multimodal teams do not need a separate vector database server. Run LanceDB inside your Python process, or on S3, and stop paying Pinecone.
Anthropic dropped Claude Sonnet 5 on June 30, 2026, and the Terminal-Bench jump (+20.7 points) is real. But the new tokenizer quietly adds ~30% to your token bill. Here's my honest take on whether the agentic hype survives contact with production.
Your self-hosted 32B is doing 80 tok/s single-stream. Speculative decoding gets you ~1.8× throughput on chat for the cost of one tiny draft model and three CLI flags — with a tokenizer-mismatch footgun that turns output into gibberish without a single warning.
Tokens got 16x cheaper between 2023 and 2026. The next three years will deliver single-digit percentage gains. HBM, power, and latency have run out of headroom — and every AI unit-economics deck is still priced for the wrong world.
Altman, Hassabis, LeCun cannot agree what AGI means. Every 'AGI benchmark' saturates in a year, the term shows up four times per LP deck, and the best 2026 agent is 31 points short of a junior engineer. AGI is fundraising.
Stop maintaining two tracing stacks. Five lines of OpenTelemetry setup pipes every LLM span — model, prompt, tokens — into self-hosted Langfuse via the OTLP HTTP endpoint, with auto-instrumentation for OpenAI and Anthropic.
Cloud OCR just died for regulated industries. Mistral OCR 4 ships 170 languages as a self-hosted container at $4 per 1,000 pages. The EU's real answer to the OpenAI and Anthropic stack monopoly.
Marimo stores notebooks as pure Python, tracks a reactive dependency graph, and runs as a script or deploys as an app from one .py file. After six weeks I'm not going back to .ipynb.
Dense retrieval hides a structural bottleneck under precision defaults and reranker hacks. ColBERT keeps per-token representation; PLAID cut the storage cost roughly 5x in a 2022 paper most teams never read. That gap is your long-tail eval failure.
Anthropic bragged about a 1M-token context. What they didn't tell you is the new tokenizer inflates token counts ~30%, so the window holds roughly 23% less text than five 200K Sonnet 4.6 windows would have — and three API fields now return hard 400s.
While the rest of the AI world fights over who has the shiniest 8-GPU inference rig, neuml/txtai shipped v9.11 two days ago with a unified embeddings database, a smolagents-backed agent layer, graph + sparse + dense indexing, and bindings in JS/Java/Rust/Go. 12,700 stars. Apache 2.0. Zero VC footprint. This is the framework you should have been benchmarking in 2026.
Every Claude Code session I open starts with the same four prompts: review the diff, write a commit message, hunt for secrets, and explain the failing test. Custom slash commands turn those into single keystrokes. Here is the directory structure, two real command files, and the three gotchas that will save you an hour.
Strip away the word "agentic" from any Series A deck that raised in the last six months and you'll find one of three things: a POST and a GET, a scheduled cron with a prompt, or a vector search returning chunks to a system prompt. A CRUD wrapper with a chat box, dressed up in marketing copy. The investor pitch is buying the abstraction; the unit economics can't survive contact with real customers.
On June 30, Meituan open-sourced LongCat-2.0 — a 1.6-trillion-parameter Mixture-of-Experts model with a native 1M-token context, MIT-licensed, trained end-to-end on a 50,000-card domestic Chinese ASIC cluster. It was already top-3 on OpenRouter as the stealth 'Owl Alpha.' Limited-time API pricing: $0.30 in / $1.20 out per million tokens, with cache hits free. The export-control era is closing.
If your first-token latency to Claude is over 600ms, you probably don't have a network problem — you have a connection-pool problem. Here's the httpx setup, the region-routing trick, and the two gotchas that make the difference between 1.8s and 280ms cold TTFB.
On July 2, 2026, Poolside open-weighted Laguna XS 2.1: a 33B total / 3B active MoE, 256 experts with top-8 routing, mixed 3:1 sliding-window + global attention, native FP8 KV cache, 256K context, and a separate DFlash speculator that doubles local tok/s. SWE-bench Multilingual 63.1% (+5.4 vs XS.2), SWE-bench Verified 70.9%, $0.10/$0.20 per MTok — half of Haiku 4.5. The first open-weights coding model I'd ship an agent on without hedging.
Models are commoditized. Data is a temporary moat. Compute is a treadmill for everyone but the labs. The only durable advantage left in AI is the one thing that cannot be trained, benchmarked, or acquired with a term sheet: taste. The companies that will win the next decade are the ones with the better eye.
OpenPipe's ART is an open-source GRPO wrapper that turns your existing Python agent code into a trainable policy, with a real production result: a Qwen 2.5 14B email agent that beats OpenAI o3 on the Enron retrieval benchmark. 10.2k stars, Apache 2.0, last commit two days ago. This is the first RL-for-agents framework I'd actually ship against.
Every 'fully autonomous' agent in 2026 ships with the dial cranked to 10 and the guardrails off. The autonomy is the bug, not the feature. Klarna just taught the industry an expensive lesson.
OpenAI put GPT-5.6 — Sol, Terra, Luna — into limited preview June 26, 2026. The Ultra mode sub-agent topology and Terminal-Bench SOTA matter more than the three-tier naming scheme.