Field notes on frontier open models.

• 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
• 2026-10-11 · upd 2026-11-06 Kimi K3 in Goose: custom provider setup in 5 minutes Run Kimi K3 in goose: one custom-provider JSON puts Wallaby at the top of the provider list. Manual route and its 404 pitfall kept. Verified on v1.54.0. Tutorial
• 2026-11-05 · upd 2026-11-06 Kimi K3.1 Pro thinking cost: what the effort dial adds to the bill Thinking tokens bill at the output rate — $10 per million on official K3.1 Pro, $9 on Wallaby. What each effort tier costs on a fixed task, why 'no budget' is not the cheap option, and how to read reasoning tokens in your own logs. Guide
• 2026-11-05 · upd 2026-11-06 Kimi K3.1 Pro cache pricing: $0.20 hits against $2.00 misses K3.1 Pro bills cached input at $0.20 per million against $2.00 for misses — a 10x gap. The hit rates where caching pays, the blended price at 90% and 93%, and the workloads caching does not save. Guide
• 2026-11-05 · upd 2026-11-06 Kimi K3.1 Pro API pricing: $2/$10 per million tokens Kimi K3.1 Pro API pricing per million tokens: $2 input, $10 output, $0.20 cached input (Wallaby: $1.80/$9.00/$0.18). The rate card, three worked examples, the Highspeed variant and the line that decides the bill. Guide
• 2026-09-13 · upd 2026-11-05 Kimi K3 API pricing: $3/$15 vs 18 providers Kimi K3 pricing, straight: $3.00/M input, $0.30/M cached, $15.00/M output at official list. What 18 API providers actually charge, and what one task costs. Guide
• 2026-11-05 K3 vs K3.1 Pro: what changes for your integration Same 1M context and chat shape. K3.1 Pro costs one-third less at list and scores 5.25 points higher on Kimi's code benchmark. Here is what changes. Guide
• 2026-11-05 · upd 2026-11-05 Kimi K3.1 Pro is out: open weights, 1M context, one-third cheaper Moonshot released the K3.1 Pro weights on 5 November: a 3T-class model with a 1M-token context, published benchmarks, and a list price one-third below K3's. Industry
• 2026-09-09 · upd 2026-11-05 Cursor "Named models unavailable": why Kimi K3 is blocked Cursor's "Named models unavailable" banner (free plans can only use Auto) is one of two walls for third-party Kimi K3. Both walls, and what works. Tutorial
• 2026-10-11 · upd 2026-11-05 Kimi K3 CLI setup: every terminal and coding tool that works, in one table Kimi K3 works in Codex CLI, Claude Code, OpenCode, pi, Crush, Goose, Hermes and more through one OpenAI-compatible endpoint. The full tool table, one-line configs, and links to each verified walkthrough. Guide
• 2026-11-03 · upd 2026-11-05 Kimi K3.1 Pro: 5,315 multilingual test results We ran 5,315 Japanese, German and Turkish tasks on Kimi K3.1 Pro. See the scores, charts, misses, evidence downloads and what they mean for business AI. Playbook
• 2026-11-05 · upd 2026-11-05 Kimi K3.1 Pro on Wallaby: 10% off and agent setup Kimi K3.1 Pro is live on Wallaby at $0.18/$1.80/$9.00 per 1M tokens. See setup, agent options, npm support and current integration limits. Guide
• 2026-11-04 We Grouped 31 Agent Memory Gates Into 9. No Checks Were Deleted. 31 agent memory gates became 9 groups. See what stayed intact, how shadow projections compared 144 rows, and which results are still under review today. Industry
• 2026-10-31 AI agent memory governance: verify every change AI agent memory governance needs more than saved notes. See nine change types, premise checks, contradiction history, weekly audits, and lossless upgrades. Playbook
• 2026-10-31 OpenHands vs OpenCode on Kimi K3: 3 runs each Same repo, same prompt, same Kimi K3 endpoint, three runs each. OpenCode finished all three at $0.053 a run; OpenHands averaged $0.070 and lost one run to a stuck loop. Guide
• 2026-10-31 A Reported $2.3 API Bill Doesn't Tell You What the Agent Costs. A reported API bill of about $2.3, a client-side reading of 159k tokens per request, and one missing denominator. Why the agent's real cost stays unknown. Playbook
• 2026-10-31 Skill Contracts vs. Ceremony: A Narrow Retest A narrow preregistered retest over 180 executions: a thin skill shell and the full scaffold were close on the clear tasks, and both arms beat no skill overall. Playbook
• 2026-10-31 The Footer Scored Zero. The Real Tool Log Gave It 20/20. Our old zero was text scoring with no tool in the loop. With a real tool, a readable ledger and a mandatory sentence, the footer scored 20/20 in 240 runs. Playbook
• 2026-10-29 Building a Letta Code custom provider: static first, live second Our Letta Code provider failed on fresh sessions until we found the real bug upstream. The 0.1.2 build log: static catalog, live models, image input, effort levels. Playbook
• 2026-10-28 Kimi K3 rate limit: three 429 causes and one lookalike A Kimi K3 429 has three official causes, plus one lookalike. Read error.type first: engine load, account tier, balance, or a retry storm. Triage order. Guide
• 2026-10-28 · upd 2026-10-28 OpenRouter alternative for Kimi K3: standing 10% off The cheapest Kimi K3 row moved while we checked. OpenRouter's floor is not a contract; our 10% off the official list is a standing rate, not a promo. Playbook
• 2026-10-28 This model does not support assistant message prefill: OpenCode's two triggers The 400 means the request ended on an assistant message. Two OpenCode paths send one, which gateways reject it, and the fixes that work today. Guide
• 2026-09-17 · upd 2026-10-28 Kimi K3 in OpenCode: zero-config, in the catalog Run Kimi K3 in OpenCode with zero config — Wallaby is in the catalog OpenCode bundles. One env var, one catalog check, K3 is selectable. Verified end to end on v2.2.0. Tutorial
• 2026-10-12 · upd 2026-10-28 GPT-5.5 retired from Codex: the six places it still hides GPT-5.5 left Codex on October 14. Six places a pinned model survives, the official replacements, and the third-party route the note skips. Start there. Guide
• 2026-10-28 · upd 2026-10-28 OpenHands sandbox failed to start within 120s: cloud and local causes The 120 second wait sits in the local app server too. What the timeout means on each side, with a 1.21 install and the runtime image cached. Guide
• 2026-10-28 · upd 2026-10-28 Codex stream disconnected before completion: two causes, one message On codex-cli 0.154.0 a dead API key and a base URL missing /v1 both end as five reconnects and the same stream error. A tested triage table for custom endpoints. Guide
• 2026-10-24 · upd 2026-10-24 Pelican on a bicycle: Kimi K3.1 Pro vs DeepSeek V4.1 Flash, measured Two SVG animations of a pelican riding a bicycle from the same one-line brief, both at maximum reasoning. One solves the legs with inverse kinematics. The other looks better and spins its wheels 2.3 times faster than the road goes. Playbook
• 2026-10-24 The Model Is Not the Bottleneck. The Routing Is. Fast and slow thinking is a routing decision, not a model-size choice. Most AI systems still leave that decision to a person with a clipboard and a hunch. Playbook
• 2026-10-01 · upd 2026-10-23 Memory Is Not Written. It's Audited. Write discipline always loosens. Three weeks in, the log claims things are done that the state file still shows in flight — and nobody notices. The fix is not stricter discipline; it's a weekly mechanical diff between what your log claims and what your state shows. Playbook
• 2026-10-23 Codex Usage Dropping? The Two Caps and 3 Ways Out Codex usage drops because two limits gate each other: a 5-hour window and a weekly cap. What each error means, why the meter burns, and three ways out. Guide
• 2026-10-19 · upd 2026-10-20 Kimi K3 in Letta Code: one mod, 5 minutes, persistent memory included Add Kimi K3 to Letta Code with one provider mod: install, /connect, pick wallaby/kimi-k3. Live model metadata, real per-token prices, verified end to end on Letta 0.34.16. Tutorial
• 2026-10-18 Why your AI agent's memory says it saved but didn't A memory call can return a saved ID and still lose the write. Three real cases, the four fixes we tried on the same bug class, and the checks that hold. Playbook
• 2026-10-17 Your Prompts Are Ad Inventory Now 404 Media's ad-buying test shows ChatGPT ads can follow conversation topics and uploaded contact lists. Five questions to ask any AI provider about your prompts. Industry
• 2026-10-17 · upd 2026-10-17 Claude Writes 90% of Claude Code. Who Reviews It? Anthropic rebuilt code review for a codebase Claude mostly writes: seven layers of checks, risk-tiered human approval, and the fix for a 50-round AI review loop. Playbook
• 2026-09-12 · upd 2026-10-17 Kimi K3 in Cline: 5-minute BYOK setup Cline's built-in catalog has included a Wallaby provider since v4.1.19: select Wallaby, paste your key, pick kimi-k3. Verified end to end on Cline v4.1.22. Tutorial
• 2026-10-06 · upd 2026-10-17 OpenHands Troubleshooting: Every Error on Your Own Endpoint, and the Fix The error map for OpenHands on your own endpoint: the cache_creation_tokens crash, first-chat stalls, $0.0000 metrics, and the settings-layer bugs. Guide
• 2026-10-06 · upd 2026-10-17 OpenHands v1.25.0 Release Notes: 17 Features, 33 Fixes OpenHands v1.25.0 ships 17 features and 33 fixes; 18 of 50 user-facing changes land in one place: LLM profiles, provider connections, the Model Router. Industry
• 2026-10-04 · upd 2026-10-17 SkillRefiner: How Offline Skill Refinement Works — and Our Production Take SkillRefiner refines agent skills offline from historical traces. We run a similar loop in production, built independently: five stages, real cases, and what it taught us back. Playbook
• 2026-10-16 · upd 2026-10-16 Kimi K3 on AMD MI355X Now Beats NVIDIA B300 per GPU: What It Does to the Price of an Agent Turn New vLLM numbers: an eight-GPU AMD Instinct MI355X system serves Kimi K3 at 24.4% more tokens per GPU than NVIDIA HGX B300 on AgentX coding-agent replay, at 46.6% lower modeled cost per token. What reaches your invoice, and when. Industry
• 2026-10-16 Claude Code Compacts Idle Sessions Now: The Off Switch, the Threshold, and What Survives Since v2.1.299, Claude Code compacts a 200K+ token conversation left idle for about 54 minutes. How to turn idle compaction off, how to tune it, and what actually survives it. Guide
• 2026-10-16 Gemini 4 Argon Is GA: the 60% Cost-per-Task Claim Has an Expiry Date Gemini 4 Argon ties GPT-6 Astra on Artificial Analysis at 60% of the cost per task — until December 1, when its price doubles. The full math, plus where the open-weight option lands. Industry
• 2026-10-16 · upd 2026-10-16 OpenAI Maintains Its Own Codebase with GPT-6 and Codex — We Priced the Same Workflow Three Ways OpenAI's Core Experimentation team merged 1,400+ cleanup PRs written by GPT-6 models. The workflow is model-agnostic. Here's what one maintenance pass costs on Astra, GPT-6.1 Sol, and Kimi K3. Guide
• 2026-10-16 Hermes now replays your model's reasoning. We tested what survives a third-party gateway. Hermes v0.22 replays prior reasoning by default across resume, branches, and compaction. We ran Kimi K3 through a third-party OpenAI-compatible gateway and checked what actually survives. Playbook
• 2026-10-16 Hermes v0.22 moved memory out of the kernel. We audited the move. Hermes v0.22 moved six memory providers (Mem0, Supermemory, Honcho, Hindsight, OpenViking, Holographic) out of the core into a plugin directory. We checked the migration claims on v0.22.1. Playbook
• 2026-10-16 Can Claude Code actually use other models? We tested it with Kimi K3 Half an hour, one logging proxy, and one deliberately bogus model name. Here is what Claude Code 2.1.300 really puts on the wire when you point it at Kimi K3, subagents included. Tutorial
• 2026-10-16 OpenCode now shows what every session costs — we checked it against the bill OpenCode v2.0.29 puts per-message cost and accumulated session cost directly in the desktop app. We ran a real session on Kimi K3 and reconciled the numbers against the gateway statement: exact to the sixth decimal. Industry
• 2026-10-14 · upd 2026-10-15 We Pre-Registered a Kill Rule for Our Own Product. It Fired. A falsification report from building a lifecycle tool for AI agent skills: pre-registered predictions, two failed rounds, and the one fix that went 0-for-20 to 1.8. Playbook
• 2026-10-16 · upd 2026-10-15 OpenCode 2 is out: what actually changes if you bring your own key OpenCode 2 went GA this week (v2.0.26–2.0.29). We installed v2.0.29 and ran Kimi K3 through it end to end: BYOK migrates in zero steps, but three v1 habits now break. Industry
• 2026-10-14 We Paid Claude $10 to Review Our Spec. It Sent Back a Test Harness. One spec, four isolated AI reviewers. Claude Opus 5.5 reviewed it, then built the trigger-test harness it had recommended: 1,600 lines, 30 passing tests, $10.04 on the meter. Playbook
• 2026-10-14 · upd 2026-10-14 We Sent the Same Spec to Four AI Reviewers. They Agreed on Exactly Six Things. One brief, four isolated AI reviewers, six points of convergence, one public disagreement, and why convergent AI opinion is still not validation. Playbook
• 2026-10-14 A $51.77 Refactor: What a Full-Throttle Claude Opus Session Actually Buys Claude Opus 5.5 at full reasoning throttle rewrote our 1,203-line operations script in about an hour: 8/8 equivalence checks, 17 passing tests, one blown $50 credit cap. The itemised account. Playbook
• 2026-10-14 Same Skill, Opposite Effects: It Lifts Weak Models and Trips Strong Ones Four rounds of dual-model, dual-judge experiments on when structured agent skills help, when they do nothing, and when they get in the way. Playbook
• 2026-10-14 Your Skill File Is Too Big: The 6KB Line (Measured) We varied only skill file size across 28 executions. The empty-output rate jumped from 0% to 25% at 6KB, and hit 50% for the naturally bloated file. Measured rules for skill and AGENTS.md authors. Playbook
• 2026-10-13 Kimi K3 in the Vercel AI SDK: one npm package, two lines of code Add Kimi K3 to the Vercel AI SDK with one npm package: install, first call, streaming, and the actual bill. Verified end-to-end on ai 7.0.138. Tutorial
• 2026-10-13 Muse Remembers. Who Governs the Memory? Meta's Muse Wonder ships Active Memory and Active Focus. Memory is now a model feature. Four things built-in memory still cannot do, and who owns them. Industry
• 2026-10-12 Kimi K3 in the Codex Desktop App: the Custom Provider Setup Nobody Shows in the GUI The Codex desktop app has no settings page for custom model providers — but it shares the CLI's config.toml. Here's the exact setup for Kimi K3, why the model picker says Custom, and the daemon restart that makes it stick. Tutorial
• 2026-10-04 · upd 2026-10-12 Open-weight LLM pricing Oct 2026: Kimi K3, DeepSeek V4 Official per-1M-token prices for the four major open-weight model APIs, fetched from the official pricing pages on Oct 4, 2026 — plus the peak-window, context-tier and cache traps, and what a coding-agent workload actually costs on each. Guide
• 2026-10-11 · upd 2026-10-12 TRAE BYOK, tested: point TRAE at your own OpenAI-compatible endpoint in five minutes TRAE's merged release lets you bring your own model endpoint, Free plan included. We wired ours to an OpenAI-compatible API running Kimi K3 and hit every pothole on the way: the provider list that silently sends you to api.openai.com, a 4054 error that only dies when you abandon the chat, and a retry storm we could see line by line in our own bill. The working setup, the verbatim errors, and the fixes. Guide
• 2026-10-12 REA (Reverse Engineer Anything) on Kimi K3: a verified Claude Code setup Wire the REA reverse-engineering toolkit into Claude Code running Kimi K3 through Wallaby Token, with a real analysis run as the receipt. Tutorial
• 2026-10-05 · upd 2026-10-11 Where to get Kimi K3: every access route compared Kimi K3 access routes compared: official API, inference clouds, gateways, subscriptions, free tiers and self-hosting, with current prices and who each route fits. Guide
• 2026-10-11 ClinePass models vs BYOK: what a month of Kimi K3 in Cline actually costs ClinePass is a flat $9.99/month for curated open models including Kimi K3; BYOK is pay-as-you-go on your own key. With four measured same-task runs, here is the honest breakeven math. Guide
• 2026-10-11 Beam vs Kimi K3: what the challenger's own table shows Reflection AI launched Beam with a 14-benchmark table aimed straight at Kimi K3. We sell Kimi K3, so we read that table closely: both columns, who ran the numbers, and the three things nobody can check yet. Industry
• 2026-10-11 · upd 2026-10-11 TRAE + MCP, tested end to end: setup that works, a loop bug, and shared memory between agents ByteDance just merged TRAE into one app with an Agent workspace. We mounted a zero-dependency MCP server the same night and ran it through IDE chat, SOLO mode, and custom agents. Everything worked except one read instruction that sent the built-in chat into a loop. The setup, the verbatim error, the fix, and the four-tool memory server we built. Guide
• 2026-10-11 Kimi K3 in Crush: config with live cost tracking Run Kimi K3 in Crush, Charm's terminal agent, via an openai-compat provider block, with per-token prices registered so the TUI shows what each session actually cost. Verified on v0.98.1. Tutorial
• 2026-10-11 The pause tax: what is still leaking from your pi agent's Kimi K3 bill pi 1.0's codemode cut prompt tokens by roughly 40%. What remains is usage-side: cache misses after pauses, untiered thinking, and context that only grows. A metered look at one real session. Playbook
• 2026-10-08 · upd 2026-10-09 Cheapest way to run Kimi K3 API (October 2026): paid floors, free options, catches The cheapest paid Kimi K3 API access we can verify is $2.70/$0.27/$13.50 per million, an ongoing rate 10% under official list. Free routes exist and every one has a boundary. Here is where each ends. Guide
• 2026-10-08 · upd 2026-10-09 Kimi K3 cached input pricing: $0.30 per million, and when caching pays (October 2026) Kimi K3 context caching, priced: $0.30/M cache hits vs $3.00/M misses, Moonshot's write fees at $3.00 (5m) and $6.00 (1h), the 93% hit-rate math, and when caching does not help. Guide
• 2026-10-08 · upd 2026-10-09 Kimi K3 API price per 1M tokens: the full rate card (October 2026) Kimi K3's API rate card: $3.00/M input, $0.30/M cached, $15.00/M output at official list, who sells it below list, and the arithmetic on one real request. Guide
• 2026-10-09 · upd 2026-10-09 We Paid Claude to Audit Our Blog. Here's the Bill — and What We Shipped. We pointed Claude at our blog through our own gateway and told it to find what was broken. The audit cost $2.50, itemised. Within 24 hours we shipped four of its findings and rejected two suggestions with clear reasoning. Playbook
• 2026-10-09 · upd 2026-10-09 Your Rule File Says \"Later.\" That's Why It Never Happens. Our agent skipped its own registration step three times, and we kept blaming its memory. Three audits later the culprit was a single word: 'after.' Temporal wording in a rule file is not rhetoric: it is control flow. Playbook
• 2026-10-09 Same Prompt, Four Thinking Budgets, Four Bills We ran the same code-review task in Cline at four reasoning_effort tiers and metered every token through our own gateway. The cheapest run caught the headline findings; the most expensive run was the one called 'None'. Playbook
• 2026-10-09 \"Free tier can only be used from within OpenCode\": what it means and three ways out OpenCode's free tier went app-only in September 2026. The 403 FreeTierError reproduced, what changed, and three ways out, including BYOK at 10% off list. Guide
• 2026-10-08 What our own internal workloads cost on Kimi K3: a real September bill (2026) We run our own internal workloads on Kimi K3. September 2026: 3,177 requests, 4.2M tokens, $17.69 total, metered per request. The bill, broken down by task, plus the formula to estimate yours. Guide
• 2026-10-07 Layered Memory for Grok Build: Native Notes + Repo Files for Engineering Teams Grok Build's native memory handles cross-session recall. We layered a repo-file system on top for git-auditable team memory and ran both configurations through the same five tasks: what each layer covers, a phantom-memory boundary, and the habit that fixes it. Playbook
• 2026-10-07 Cline + Kimi K3: every error we've hit, and the fix Every Kimi K3 error we have hit in Cline: Invalid API Response, 128K context fallback, $0.00 cost displays, cost gaps vs your bill, and 429s, with fixes. Guide
• 2026-10-06 We Ran Our Memory System Inside Hermes. It Already Had One. Hermes Agent grows its own memory: sessions get distilled into skills over SQLite FTS, tended by a Curator. We installed our file-based memory discipline into v0.21.5 anyway. Three verified mechanics, one caveat from the issue tracker, and a clear answer on which layer does what. Playbook
• 2026-10-06 Run pi with Kimi K3 on Windows or Mac: three commands, no config files Install pi with Kimi K3 on Windows or Mac: one npm extension, three commands, no config files. Verified end-to-end on pi 1.0.4, with billing to match. Tutorial
• 2026-10-06 OpenHands Model Router on your own endpoint: what works, what isn't wired yet, what it costs Day-one field test of OpenHands' Model Router on a custom endpoint: routing works at $0.0025 a call, but two early-build gaps are worth knowing first. Guide
• 2026-10-06 Kimi K3 API with per-request itemized billing Wallaby Token bills every Kimi K3 call as its own line item: input, cached input, output and thinking, in your console seconds after the request. Guide
• 2026-10-06 Kimi K3 API with a free trial credit: $0.50, no card, no top-up Every new Wallaby Token account gets $0.50 of free trial credit for the Kimi K3 API — no card, no top-up. Here's what $0.50 buys and how to make your first call in two minutes. Guide
• 2026-10-06 AI Memory Should Have a Probation Period Trust-building mode: new memories get proposed, not written, until you approve them. Plus a conditional code-version module and a full Chinese edition. Playbook
• 2026-10-05 Kimi K3 API that takes card payment (no crypto) Pay for a Kimi K3 API with a normal bank card: USD card checkout via Stripe, prepaid credits that never expire, and no crypto anywhere in the payment flow. Guide
• 2026-10-05 Kimi K3 API with a public status page: live uptime, 90-day history, JSON feed Wallaby Token publishes a public status page for the Kimi K3 API: per-component uptime over 24 hours, 30 and 90 days, live latency, incident history, and a machine-readable status.json. No login required. Guide
• 2026-10-05 AI Memory Benchmarks Measure the Wrong Thing Every major AI memory system posts green benchmark scores, and every agent user reports the same failures. The gap is structural: benchmarks test retrieval, while production memory dies of rot. Playbook
• 2026-10-05 Why your agent's token bill keeps growing, and how to audit it An agent's daily token spend can double with no change in workload. The causes are measurable once you count per request instead of per day. A field guide with real numbers and a cost simulator. Playbook
• 2026-10-01 AI Memory Pricing: Supermemory vs Mem0 vs Zep vs Letta AI memory pricing compared from all four official pages — Supermemory, Mem0, Zep, Letta — plus the self-hosted route we benchmarked and the free file option. Playbook
• 2026-10-01 AI Memory: Three Routes, Three Bills Three routes to AI memory — hosted API, self-hosted engine, plain files — and what each one bills you. We benchmarked the hot one, then said no. Playbook
• 2026-10-01 Your Agent Needs Sleep, Not a Bigger Context A stale card on our project board exposed the real bug: we had built our AI a perfect memory, and perfect memory was the problem. Human memory works because it forgets — so we rebuilt ours around sleep, pruning, and myelin. Playbook
• 2026-10-01 Memory Consolidation for AI Agents: A Three-Piece Playbook A working recipe for agent memory that gets more accurate over time: a replay job that decides what survives the day, a pruning pass that deletes on purpose, and a reflex layer that turns repeated procedures into muscle. Playbook
• 2026-09-30 Microsoft put 1,024 AI agents on one task. What did it cost? Microsoft's Agensh paper scales one task from 1 agent to 1,024 with no orchestrator. The gains are real but sharply sublinear — and the token bill appears nowhere in the paper. Industry
• 2026-09-30 Why did reasoning_effort silently stop working? For 13 days we thought the model ignored reasoning_effort. The truth: our own router was dropping the parameter. A postmortem with logs, retests, and the fix. Playbook
• 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 OpenHands 'Failed to load provider connections': fix OpenHands 'Failed to load provider connections'? Two agent-servers sharing ~/.openhands use different OH_SECRET_KEY values, so saved keys read empty. Fix: one value per machine. 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 OpenHands 'cache_creation_tokens' AttributeError: fix OpenHands: 'PromptTokensDetailsWrapper' object has no attribute 'cache_creation_tokens' — an SDK/LiteLLM version-skew bug, not your endpoint. Cause and fix inside. Tutorial
• 2026-09-23 OpenHands stuck at 'Running task'? The first-chat stall OpenHands stuck at 'Running task' / 'Waiting for task'? The call succeeded — the UI event channel is rate-limited. Fix: stop, start a fresh conversation. Why Metrics shows $0.0000, too. 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 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 How to compare LLM API costs: measure cost per accepted output LLM API cost comparison goes past price per million tokens: retries and human fixes are the bigger bill. Measure cost per accepted output in one afternoon. Playbook
• 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
• 2026-09-10 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

No posts match. Try a different keyword or tag.