Field notes on frontier open models.

Field notes on frontier open models — prices, benchmarks, and what we run in production.

2026-09-09 Why we built Wallaby — and where we're going Wallaby exists because access to frontier open-weight models is harder than it should be. What we run, what we charge, and reliability you can verify. PinnedCompany
2026-09-29 Your API key is probably already on GitHub Searching GitHub for OPENAI_API_KEY returns thousands of committed .env files — many still live. Five boring fixes that actually protect your keys. Guide
2026-09-29 It Remembers Because You Close Memory systems don't fail at install — they fail at the end of each session, one skipped write-back at a time. The fix is a two-minute closeout ritual, and it now ships as a paste-in prompt. Playbook
2026-09-29 AI Reviews AI: We Planted 7 Bugs in a Rate Limiter and Sealed the Answer Key One agent wrote a token-bucket rate limiter with 7 planted bugs. Another agent — Kimi K3 in OpenHands Agent Canvas — reviewed it. It caught 6, spotted the rigged test, and found 2 bugs we didn't plant. Full scorecard and the $0.16 bill. Tutorial
2026-09-28 OpenHands Agent Canvas: Scheduled Slack Digests Wire an Agent Canvas cron automation to Slack via an incoming webhook: a self-contained prompt, a real verified run, metered cost, and two environment notes. Tutorial
2026-09-28 The Authors Guild filings are an API procurement problem Unsealed briefs in Authors Guild v. OpenAI quote executives admitting they trained on pirated books. Two questions every API buyer should now ask their provider — provenance and retention. Industry
2026-09-25 Your OpenHands Agent Has Amnesia. Fix It. OpenHands reserves an AGENTS.md slot but ships no method. We filled it with a real memory protocol, ran it on a remote agent-server, and kept the receipts. Playbook
2026-09-25 How to Use Kimi K3 in pi (One JSON Block) How to use Kimi K3 in pi: one JSON block in ~/.pi/agent/models.json, one exported key, done. Verified end-to-end on pi 0.86.1 with billing logs to match. Tutorial
2026-09-25 Your AGENTS.md Is Rotting (Here's the Fix) AGENTS.md rots by default: stale decisions, invented paths, confident lies. Structure won't fix it — a maintenance layer will. Here's ours, in production. Playbook
2026-09-25 Kimi K3 in OpenHands Agent Canvas (Step-by-Step) Point OpenHands Agent Canvas at Kimi K3 through an OpenAI-compatible endpoint: three fields, a real 40-second task with metered cost, and two gotchas. Tutorial
2026-09-23 Kimi K3 in OpenHands: 5-minute setup Point OpenHands at the kimi-k3 reasoning model through an OpenAI-compatible API — one LLM profile, three fields, verified end to end on a real account. Tutorial
2026-09-21 AI remembers, you find: fixing AI memory rot AI memory rots mid-project: settled decisions get relitigated, files get invented. Wallaby-agent-rules v2 moves memory to plain, dated, sourced files. Playbook
2026-09-17 Kimi K3 in OpenCode: zero-config, in the catalog Run Kimi K3 in OpenCode with zero config — Wallaby is in the models.dev catalog. One env var, one model refresh, K3 is selectable. Verified end to end. Tutorial
2026-09-17 One endpoint, one bill: Kimi K3 for dev teams One endpoint, one bill: give every developer their own API key with a hard budget cap, all from one shared prepaid balance — no seat licenses, no surprise. Tutorial
2026-09-17 Union Alpha Free in OpenCode: how to try it Union Alpha Free in OpenCode: zero-cost model, 262k context, no key required. How to enable it, what we verified, and honest caveats before real work. Tutorial
2026-09-14 The cheapest API is the one you don't redo Per-token price is the visible cost of an LLM; rework is the bigger one. Why cost per accepted output is the unit that matters — and how to measure yours. Playbook
2026-09-13 Kimi K3 API pricing compared: 17 providers Kimi K3 API pricing compared: 17 providers, with input, cached-input and output prices per million tokens, plus a blended workload cost for coding agents. Guide
2026-09-13 AGENTS.md as a token budget: the forbidden list AGENTS.md is a Linux-Foundation standard read by 30+ coding agents. Used well it's a token budget — our full production playbook, forbidden list included. Playbook
2026-09-13 Kimi K3 in Codex CLI: profile-file setup Run Kimi K3 in OpenAI Codex CLI through Wallaby's API, using the profile file — one config file, verified end to end with a real coding task. Tutorial
2026-09-12 Kimi K3 in VS Code Copilot via BYOK: setup Point VS Code's Bring Your Own Key endpoint at an OpenAI-compatible API and run kimi-k3 in Copilot Chat agent mode — full setup with working configuration. Tutorial
2026-09-12 Kimi K3 in Cline: 5-minute BYOK setup Configure Cline to use the kimi-k3 reasoning model through Wallaby Token's OpenAI-compatible API. Working setup in under five minutes, verified end to end. Tutorial
2026-09-10 Kimi K3 in Hermes Agent: 4 lines of YAML Point Hermes Agent at the kimi-k3 reasoning model through Wallaby Token's OpenAI-compatible API. Verified end-to-end — chat and tool use both work. Tutorial
2026-09-09 Top up Wallaby Token: card, Apple & Google Pay How to add credit to your Wallaby Token account with a card, Apple Pay, or Google Pay — plus the pitfalls we hit ourselves when testing. Guide
2026-09-09 Kimi K3 in Claude Code: 5-minute setup Configure Claude Code to run Moonshot AI's kimi-k3 model through Wallaby Token's Anthropic-compatible endpoint, verified end-to-end. Tutorial
2026-09-09 Kimi K3 in Cursor: what blocks it, what works Running Kimi K3 in Cursor via an OpenAI-compatible endpoint hits two hard blocks today — here is exactly what we hit, and the setup that works instead. Tutorial