Every AI coding agent installed across the fleet — how they differ, what models they reach, and where the free quota lives.
agentic-coding/tools/ai-inventory/harnesses.html
Google stops serving Gemini Code Assist + Gemini CLI for individual/Pro/Ultra tiers on 2026-06-18. Everything moves to Antigravity + Antigravity CLI. Our gemini --yolo alias and ai-launcher option 11 break that day — migrate before then.
gpt-5.2; ran GPT-5.3-Codex to tbench rank 6.agy CLI) — free model picker incl. Claude Opus 4.6 (Thinking), Claude Sonnet 4.6 (Thinking), Gemini 3.1 Pro (Low/High), Gemini 3.5 Flash (Low/Med/High), GPT-OSS 120B. Free Opus 4.6 — effectively replaces the lost Copilot premium lane. Google-account sign-in (agy to log in), weekly limits, unlimited tab completions.wetheflywheel account (which held the 1,500 premium-req/mo sub) was DELETED 2026-06-20. Only thomas-prommer remains, on Copilot Free (GPT-5 mini / Haiku, 0 premium interactions, ~200 chat + 2,000 completions/mo, resets monthly). No GPT-5.3-Codex / Sonnet / Gemini-Pro lane until a new sub is set up. The copilot alias no longer pins a token.kimi-k2:free — zero-cost Kimi via aid-kimi-free.| Harness | Type | Machines | Version | Auth / billing | Models | What makes it different |
|---|---|---|---|---|---|---|
| Claude Code | Terminal agent | hcm fue muc sin | 2.1.163 |
2× Claude Max subs (Max 20x + Max 5x, cs switcher) |
Opus 4.8 (1M ctx), Sonnet 4.6, Haiku 4.5 | Primary harness. Deepest scaffolding: skills, hooks, agent teams, workflows, cron. Everything else is overflow/experiment. |
| Codex CLI | Terminal agent | hcm muc | 0.133.0 |
OpenAI API key (usage-billed; no sub) | GPT-5.4, GPT-5.3-Codex | OpenAI's own agent. Aliases: codex (full-auto), ccodex (danger-full-access + web search). Codex Plus sub ($20) evaluated, not bought. |
| OpenCode | Terminal agent (multi-provider) | hcm | 1.3.17 |
Per-provider: OpenRouter (default), Copilot OAuth, Moonshot | Default z-ai/glm-5.1 / z-ai/glm-5-turbo via OpenRouter; via aliases: Copilot Sonnet 4.6 (oc-gh), Kimi K2.5 (oc-kimi), GPT-5.4 (oc-gpt54), Grok 4 (oc-grok) |
The model-router: one harness, every key. How we burned the 300 Copilot premium requests on Opus 4.6. Cheap overflow lane = GLM-5.1 (now metered via OpenRouter — Z.ai coding plan expired 2026-06-07). |
| Copilot CLI | Terminal agent | hcm | 0.0.411 |
Copilot Free only — wetheflywheel (paid sub) deleted 2026-06-20; thomas-prommer is the sole account, 0 premium req/mo |
Free tier: GPT-5 mini, Haiku. No GPT-5.3-Codex / Sonnet / Gemini-Pro / Opus (all were premium-only) | Premium lane dead with the account. copilot alias no longer pins a token — runs on thomas-prommer Free. oc-gh shares the same (now free) pool. |
| Droid (Factory) | Terminal agent | hcm fue muc | 0.74.0 |
Factory account — included free quota | GPT-5.2 (default), GPT-5.3-Codex, Claude, Gemini | Terminal-Bench 2.0 rank 6 (GPT-5.3-Codex). Shares our commands/agents via ~/.factory symlinks. droid --auto high. |
| Amp (Sourcegraph) | Terminal agent + editor ext | fue muc | 2026-06-04 build |
Amp Free (free daily allowance) or credits | Deep mode = GPT-5.3-Codex; Oracle reasoning = GPT-5.x | The "free codex quota" harness. Auto-upgraded by upgrade-coding-agents.sh since 2025-12. Free allowance recently reshaped (paused for inactive users) — re-login to verify. |
| Devin CLI | Terminal agent + cloud VM | hcm | 2026.5.6 |
Cognition account; 10 free ACUs (cloud), local CLI free | Cognition's own model stack (Devin / SWE-family) | Two modes: local terminal agent (codename "chisel") + cloud sessions that open PRs from a VM. Yolo: DEVIN_PERMISSION_MODE=dangerous (set globally). Tested against domain-ops#1. |
| Gemini CLI | Terminal agent | hcm | 0.29.0 |
Google account — free tier | Gemini 3 Pro / Flash | EOL 2026-06-18. Replaced by Antigravity CLI. Aliases gemini (yolo), gemini-auto. |
Antigravity (+agy) |
IDE (VSCode fork), multi-agent | hcm | IDE 1.21.9 / agy 1.107 |
Google account — free plan (weekly limits, 3×'d twice in May) | Gemini 3 Pro, 3.5 Flash; unlimited tab completions | IDE-first agent manager with browser integration; agy just launches the IDE. Used for detailed code reviews when other quota ran out. |
| Qwen Code | Terminal agent (Gemini CLI fork) | hcm | 0.10.3 |
Qwen OAuth — 2,000 req/day free | Qwen3-Coder family | Biggest raw free allowance in the fleet. qwen --yolo in ai-launcher. |
| Aider | Terminal pair-programmer | hcm | 0.86.2 |
BYO key (OpenRouter default) | Default glm-5.1; aliases for Kimi, Sonnet, o3, o4-mini, kimi-k2:free |
Leanest overhead, git-native diffs, repo-map. Terminal-Bench pickup (Apr 2026) for cheap-model overflow work. |
| Goose (Block) | Terminal agent + extensions | hcm | 1.29.1 |
BYO key — provider never configured | Any (Anthropic, OpenAI, OpenRouter, Ollama…) | Extension/MCP-heavy architecture, subagent "summon". Second Terminal-Bench pickup (Apr 2026); still unconfigured — finish or remove. |
| Hermes (Nous) | Assistant gateway (channels + agent) | hcm muc | 0.13.0 |
Credential pool: Anthropic OAuth ✓, Copilot gh-token, MiniMax key | muc default: MiniMax-M2.7; supports Nous Portal, Kimi, GLM, OpenRouter, Gemini, xAI | Not a coding CLI — the OpenClaw successor: WhatsApp/Slack/Discord channels, kanban, cron, self-improving skills. See Hermes section below. |
| OpenClaw | Assistant gateway | hcm | 2026.4.2 |
— | Legacy — migrated to Hermes (May 11). Archive with hermes claw migrate cleanup. |
|
Hermes (NousResearch hermes-agent) is our personal-assistant gateway, not a coding harness: it owns the WhatsApp/Slack/Discord/iMessage channels, a kanban, cron jobs, and self-improving skills. It migrated from OpenClaw on 2026-05-11 and runs on hcm + muc (muc is the live gateway).
MiniMax-M2.7 (provider minimax, MINIMAX_API_KEY)gh), claude_code providermedium, 60 max turns, gateway timeouts tuned for channel usekimi-coding (KIMI_API_KEY) and kimi-coding-cn (KIMI_CN_API_KEY) — wired in config, ready to activateKIMI_API_KEY + MOONSHOT_API_KEY re-added to BAO (secret/library/ai) on 2026-06-06 and verified live against api.moonshot.ai — all machines pick it up via the env.shared cronaid-kimi-free → OpenRouter kimi-k2:free| Model family | Reachable through | Cost lane |
|---|---|---|
| Claude Opus 4.8 / Sonnet 4.6 / Haiku 4.5 | Claude Code (2 Max subs) · Hermes (Anthropic OAuth) · Antigravity free (Opus 4.6 + Sonnet 4.6, Thinking) — Copilot premium-req lane gone (wetheflywheel deleted 2026-06-20) | Subscription + Antigravity free |
| GPT-5.4 / GPT-5.3-Codex | Codex CLI (API key) · Amp deep mode (free) · Droid (Factory quota) · oc-gpt54 — Copilot CLI premium lane gone (wetheflywheel deleted) | Metered via API; free via Amp/Droid |
| Gemini 3 Pro / 3.5 Flash | Antigravity (free, weekly) · Gemini CLI (until 06-18) · Hermes (GOOGLE_API_KEY) | Free tier |
| GLM-5.1 / GLM-5-turbo (Z.ai) | OpenCode default · Aider default — both via OpenRouter · Hermes zai provider (API key) | OpenRouter metered — the cheap overflow lane. Z.ai coding plan expired 2026-06-07 (unused since April), not renewed |
| Kimi K2.5 (Moonshot) | oc-kimi · aid-kimi · Hermes kimi-coding — key re-export pending · kimi-k2:free via OpenRouter | Prepaid credits (unconsumed) / free tier |
| MiniMax M2.7 | Hermes on muc (default) | API key |
| Grok 4 | oc-grok (XAI_API_KEY) · Hermes xai provider | API key |
| Qwen3-Coder | Qwen Code CLI | Free (2,000/day) |
| DeepSeek + 100s more | OpenRouter key → Aider, OpenCode, Goose, Hermes | Metered, cheap |
| Local (LLaVA, Whisper, Qwen via Ollama) | Ollama on hcm — /video skill etc. | Free, offline |
The wetheflywheel account holding this paid AI-credit plan was deleted 2026-06-20. None of these premium models are reachable now — Copilot is Free-tier only (GPT-5 mini / Haiku). Table kept for reference if a new sub is set up.
1 AI credit = $0.01. Prices per 1M tokens; "credits/request" assumes a typical agentic turn of ~20K input + 2K output, uncached. Source: GitHub models & pricing, June 2026 billing.
| Model | Input | Cached in | Output | ~Credits/request | vs cheapest |
|---|---|---|---|---|---|
| GPT-5 mini | $0.25 | $0.025 | $2.00 | ~0.9 | 1× |
| GPT-5.4 mini | $0.75 | $0.075 | $4.50 | ~2.4 | 2.7× |
| Claude Haiku 4.5 | $1.00 | $0.10 | $5.00 | ~3.0 | 3.3× |
| Gemini 3.5 Flash | $1.50 | $0.15 | $9.00 | ~4.8 | 5.3× |
| GPT-5.3-Codex ← default for real work | $1.75 | $0.175 | $14.00 | ~6.3 | 7× |
| Gemini 3.1 Pro (≤200K) | $2.00 | $0.20 | $12.00 | ~6.4 | 7.1× |
| GPT-5.4 (≤272K) | $2.50 | $0.25 | $15.00 | ~8.0 | 8.9× |
| Claude Sonnet 4.6 / 4.5 | $3.00 | $0.30 | $15.00 | ~9.0 | 10× |
thomas-prommer): gh api copilot_internal/user --jq '.quota_snapshots.premium_interactions | "\(.remaining)/\(.entitlement)"' → currently 0/0.scripts/upgrade-coding-agents.sh (cron/systemd timer) keeps Claude Code, Codex, Gemini, Copilot, OpenCode, Qwen, Droid and Amp current on all machines.ai → scripts/ai-launcher.sh menu with per-provider quota display (Claude / OpenAI / Gemini).wetheflywheel account that held the 1,500/mo shared pool (Copilot CLI / VS Code / oc-gh) was deleted 2026-06-20. Only thomas-prommer remains, on Copilot Free (0 premium interactions). No new paid GitHub account was set up to replace it; GitHub Pro signups remain paused. For codex-class work use Amp deep mode (free, fue/muc) or Droid instead.amp once on muc to confirm the free allowance wasn't paused for inactivity.