Adoption dailyAgent stackAI coding
Today's story: Claude Code
Claude Code climbs as AI coding tools race
Claude Code jumps to No. 6 with 2.4M daily installs, while OpenAI Codex hits 3.9M. The gap between coding agents and general AI APIs narrows.
The numbers: Claude Code is today's biggest mover: up 4 places to No. 6, Hacker News stories at 1.29× the four-week pace. Claude Code: 1.18× momentum across 2 signals. 6 of 21 trends are climbing and 4 are cooling. SpaceX Starship still leads the board at 1.87× (day 6).
Backfilled on October 7, 2026 using only data published by October 6, 2026.
Claude Code, signal by signal
Each pedestal is one signal: its height is last week's typical day against the four weeks before, and the ring marks that normal. A lit pedestal is rising 1.15× or more.
Claude Code is today's biggest mover: up 4 places to No. 6, Hacker News stories at 1.29× the four-week pace.
Claude Code: 8.3 Hacker News stories a day on a typical day last week, against 6.4 the four weeks before
Bars are single days, the line is the 7-day average, the shaded band is the last 7 days and the dashed line is the four-week typical day (median).
Data through npm 10/04, Wikipedia 10/05, HN 10/05. Source: Hacker News search (Algolia), story titles.
Claude Code is today’s biggest mover, climbing four places to No. 6 with 2.4M/day installs. Hacker News activity hits 8.3/day, a 1.29× increase over the four-week pace. This surge places it ahead of OpenAI Codex, which holds No. 3 with 3.9M/day installs. Both tools show strong momentum, with Codex at 1.23× and Claude Code at 1.18×. The competition defines the current coding agent market.
OpenAI Codex leads in raw volume, recording 3.9M/day installs against 3.4M previously. Its Wikipedia interest is low at 69/day, but HN stories rise to 5.6/day. Meanwhile, AI API SDKs reach 21M/day installs, and Model Context Protocol hits 12M/day. These underlying layers support the coding tools, showing that the ecosystem is growing beneath the specific applications. The numbers confirm a broad expansion in AI development tools.
Starship remains No. 1 with 1.87× momentum, but the focus shifts to software. Passkeys reach 1.0M/day installs, climbing steadily. The rise of Claude Code and Codex indicates that developers are integrating AI directly into their workflows. This is not just about chat interfaces; it is about executable code generation. The adoption board shows a clear preference for tools that write and debug code, signaling a practical turn in AI usage.
Watch next: Watch if Claude Code’s Hacker News engagement sustains above 8.0/day to confirm the climb.
Column drafted by qwen/qwen3.8-27b from the numbers below; every figure checked against them.
The numbers
Hacker News carried 8.3 stories a day with "Claude Code" in the title last week, against 6.4 a day in the four weeks before (1.29×). On a typical day last week, npm installs of @anthropic-ai/claude-code reached 2.4M, 1.08× the 2.3M of a typical day in the four weeks before.
Still No. 1 for day 6: SpaceX Starship at 1.87×, with Wikipedia readers at 1.87× (2,580 on a typical day against 1,378).
Quiet adoption: Local LLMs installs run at 1.13× their four-week pace while attention sits at 0.9×. Developers are adding it faster than people are reading about it.
Cooling fastest: Smart glasses at 0.67×, with Wikipedia readers down to 153 on a typical day from 228.
The long view: OpenAI Codex installs over the last four weeks are 116× the same four weeks a year earlier (3.4M a day against 29k).
Trend pages: SpaceX StarshipPasskeysOpenAI CodexSmart glasses
Quiet adoptionBroad riseOne-day spike6 of 21 trends are climbing; SpaceX Starship leads at 1.87×
Momentum is a typical day (median) of the last 7 divided by a typical day of the 28 before, averaged across every signal with enough data. 1× means no change. Rings mark each signal.
Data through npm 10/04, Wikipedia 10/05, HN 10/05. Source: npm downloads API, Wikimedia pageviews, Hacker News search.
5 of 7 developer tools are being installed faster than they are being read about
Across: attention momentum (Wikipedia readers and Hacker News stories). Up: install momentum (npm). Both on log scales; the 1× lines split the corners.
Data through npm 10/04, Wikipedia 10/05, HN 10/05. Source: npm downloads API, Wikimedia pageviews, Hacker News search.
SpaceX Starship draws the most Wikipedia readers against its own normal: 1.87× over the last week
Each cell is one day's readers divided by that trend's four-week typical day. Brighter runs hot, darker runs cold.
Data through npm 10/04, Wikipedia 10/05, HN 10/05. Source: Wikimedia pageviews API, user agents only.
Every number on the board
| SpaceX Starship | Space | 1.87× | Breakout | – | – | 2,580 | 1.87× | 0.3 | 0.5×* | 0 |
|---|---|---|---|---|---|---|---|---|---|---|
| Passkeys | Web platform | 1.31× | Climbing | 1.0M | 1.31× | 86 | 0.97×* | 0.0 | 0×* | 0 |
| OpenAI Codex | AI coding | 1.23× | Climbing | 3.9M | 1.16× | 69 | 1.79×* | 5.6 | 1.31× | 0 |
| AI API SDKs | AI agents | 1.21× | Climbing | 21M | 1.21× | – | – | – | – | 0 |
| Model Context Protocol | AI agents | 1.19× | Climbing | 12M | 1.23× | 1,663 | 1.14× | 8.0 | 1.2× | 0 |
| Claude Code | AI coding | 1.18× | Climbing | 2.4M | 1.08× | – | – | 8.3 | 1.29× | 0 |
| WebGPU | Web platform | 1.14× | Steady | 1.7M | 1.23× | 137 | 1.06× | 0.7 | 0.95×* | 0 |
| Solid-state batteries | Energy | 1.14× | Steady | – | – | 453 | 1.14× | 0.0 | 0×* | 1 |
| Bun runtime | Web platform | 1.11× | Steady | 758k | 1.19× | 244 | 1.03× | 1.0 | 1.12×* | 0 |
| Starlink | Space | 1.11× | Steady | – | – | 2,216 | 1.11× | 0.7 | 1.43×* | 0 |
| AI agents | AI agents | 1.1× | Steady | 755k | 1.25× | 962 | 0.81× | 15 | 1.29× | 0 |
| Small modular reactors | Energy | 1.1× | Steady | – | – | 510 | 1.1× | 0.0 | n/a* | 0 |
| Gemini CLI | AI coding | 1.09× | Steady | 70k | 1.09× | – | – | 0.0 | n/a* | 0 |
| Heat pumps | Energy | 1.06× | Steady | – | – | 502 | 1.06× | 0.0 | 0×* | 0 |
| Local LLMs | AI agents | 1× | Steady | 192k | 1.13× | 634 | 0.9× | 0.7 | 1.05×* | 0 |
| Vibe coding | AI coding | 0.93× | Steady | – | – | 1,755 | 1.2× | 0.9 | 0.73× | 0 |
| eVTOL air taxis | Space | 0.9× | Steady | – | – | 181 | 0.9× | 0.0 | 0×* | 0 |
| Humanoid robots | Robots | 0.81× | Cooling | – | – | 301 | 0.81× | 1.0 | 1.22×* | 0 |
| Quantum computing | Devices | 0.8× | Cooling | – | – | 1,700 | 0.96× | 2.0 | 0.66× | 0 |
| Robotaxis | Robots | 0.71× | Cooling | – | – | 178 | 0.71× | 0.9 | 2.2×* | 1 |
| Smart glasses | Devices | 0.67× | Cooling | – | – | 153 | 0.67× | 0.7 | 1×* | 0 |
| Vehicle-to-grid | Energy | n/a | Not enough data | – | – | 58 | 0.92×* | 0.0 | 0×* | 0 |
Method and sources
Every trend gets up to three free, daily signals. Installs: npm registry downloads for the packages named on each trend page (developer adoption; it counts CI and mirrors too, so it measures direction, not people). Attention: English Wikipedia readers per day, human agents only, and Hacker News stories with the term in the title. For each signal we divide a typical day (the median) of the last 7 complete days by a typical day of the 28 days before. Medians keep one launch-day spike from carrying a whole week; both windows are whole weeks, so weekend dips sit equally in both. Momentum is the geometric mean of the signals that clear a minimum base. npm reports some days as zero for every package at once; we treat those as missing.
The column is drafted by a free language model from the day's computed facts only, and is published only if every number in it matches those facts; otherwise the computed paragraphs stand alone. Theme labels come from Jev (or its Cloudflare Clef fallback, as noted) choosing from a fixed list of ten.
Stages: Breakout 1.5× and up, Climbing 1.15×, Steady 0.87× to 1.15×, Cooling below. Raw data: /api/trends/2026-10-06.json.