Skip to content
PluginStats

@trymesh/cli weekly downloads statistics

By trymesh · npm · MCP servers

Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.

View on npm Fresh · Oct 27, 2026 · data Jul 1, 2026

@trymesh/cli has 276 recorded weekly downloads on npm.

Weekly downloads
276
Official API · Jul 1, 2026
7-day growth
—
Insufficient history
30-day growth
—
Insufficient history
90-day growth
—
Insufficient history
Rank
—
Among tracked npm listings

About @trymesh/cli

<div align="center"> <img src="https://cdn.jsdelivr.net/npm/@trymesh/cli/assets/mesh-banner.png" alt="Mesh — terminal-first AI engineering agent" width="100%" /> </div> <div align="center">

npm node

try-mesh.com · Docs

</div>

Mesh is a terminal agent built to spend fewer tokens on the same work.

Most coding agents resend the whole chat, bloated tool schemas, and redundant file reads every turn. Mesh compacts what goes into the model — tool specs, transcript history, workspace context — so multi-step tasks stay cheap and fast. Same gateway, same models, less noise in the prompt.

npm install -g @trymesh/cli
mesh

On first run, mesh opens sign-in in your browser. Default model is Gemini 3.5 Flash. Requires Node 20+.

Why Mesh

  • Fewer tokens per turn. Compacted tool definitions, session capsules, and context planning cut prompt size versus a raw agent loop — often by a large margin on longer sessions.
  • Cheaper models when it fits. Flash-Lite auto-routing and /model let you trade speed vs. depth without leaving the session.
  • Search before you read. /index builds a workspace index so the agent can grep and search instead of dumping whole files into context.
  • One install, one account. Sign in once; model calls go through the shared Mesh gateway on try-mesh.com.
  • Many models, one session. Gemini, Grok, GLM, Kimi, DeepSeek, Qwen, Llama, and more via /model or --model <alias>.

Benchmarks

Head-to-head on a real multi-turn task (nextjs-full, 3 turns, Gemini 3.5 Flash) — Mesh vs a raw LLM loop on the same model and prompts.

nextjs-full · 3 turns · Gemini 3.5 Flash

Input tokens sent to the model   (lower is better)
  Mesh   ██████████                            27.4K
  Raw    ████████████████████████████████████  94.6K     −71%

Wall-clock time
  Mesh   ██████████████████████                60.0s
  Raw    ████████████████████████████████████  96.7s     −38%
TurnMeshRawReduction
14.6K7.6K−39%
28.9K56.0K−84%
313.9K31.1K−55%
Total27.4K94.6K−71%

Replay with mesh eval. Raw baseline uses provider prompt caching, so Mesh’s advantage is conservative.

Quickstart

npm install -g @trymesh/cli
mesh
mesh "fix the failing auth test"
mesh resume
mesh --resume <session-id>

mesh starts the interactive terminal UI. Pass a quoted task for a one-shot run. Use /help in a session for the full command list.

Commands

CommandWhat it does
meshInteractive session (sign-in on first run)
mesh "<task>"One-shot task, then exit
mesh resumeResume the latest session in this workspace
mesh --resume <id>Resume a specific session
mesh logout / mesh whoamiSign out · show signed-in email
mesh doctor [fix]Diagnose the install
mesh eval [--since <ISO>]Replay turns and measure token efficiency
mesh supportDebug info for bug reports

In-session — the five worth knowing:

CommandWhat it does
/costToken spend and savings this session
/dashboardLive repo dashboard in the browser
/modelSwitch model (cost vs. quality)
/indexBuild or repair the workspace search index
/helpFull command reference

Models

Default: Gemini 3.5 Flash. Pick another with /model or mesh --model <alias>.

ModelAliasNotes
Gemini 3.5 Flashdefault, 3.5-flashDefault — fast
Gemini 3.1 Pro Preview3.1-proStronger reasoning
Gemini 2.5 ProproStable reasoning
Gemini 2.5 Flash-LiteliteCheapest — auto-routed on trivial turns
Grok 4.20 Reasoninggrok-reasoningxAI reasoning
Grok 4.20 Non-Reasoninggrok, grok-fastxAI low-latency
GLM 5glmZ.ai
Kimi K2.6kimiMoonshot
DeepSeek V4 ProdeepseekGeneralist
Qwen 3 CoderqwenCode specialist
Llama 4llama, maverickMeta MoE
GPT-OSS 120Bgpt-ossOpen weights

If the primary model errors out, Mesh tries Gemini 2.5 Pro, then Kimi K2.6.

Account

  1. Go to try-mesh.com and create an account (free tier available).
  2. Run mesh in your project — the CLI opens browser sign-in and stores your session in the OS keychain (with a ~/.config/mesh fallback).
  3. Pro plan: email edgar.baumann@try-mesh.com or philipp.horn@try-mesh.com to request access.

Your prompts and code context are sent to the model provider you select to generate responses. Run mesh logout to clear local credentials.

Requirements

Links

try-mesh.com · Docs · Changelog

Contact

License

Mesh Commercial License — see LICENSE.

Description from the npm listing.

  • ai
  • ai-agent
  • agent
  • agentic
  • autonomous-agent
  • coding-agent
  • ai-coding-assistant
  • coding-assistant
  • pair-programming
  • developer-tools
  • devtools
  • cli
  • command-line
  • terminal
  • tui
  • repl
  • llm
  • llm-agent
  • gpt
  • chatgpt

README badge

Show your rank in a README or on your website. The badge updates automatically.

Charts

Images: 30d · 1y · all time · 1600×900 dark

Adoption over time

@trymesh/cli weekly downloads on npm, last 90 days: 276 weekly downloads as of Jul 1, 2026.@trymesh/cliWeekly downloads on npm · Last 90 days276downloads / weekNo observations recorded in this periodno observations · 0 observations · Updated Jul 1, 2026pluginstats.com
@trymesh/cli weekly downloads on npm, last 90 days: 276 weekly downloads as of Jul 1, 2026.

7/30/90-day growth

@trymesh/cli weekly downloads growth on npm: 7-day growth unavailable, 30-day growth unavailable, 90-day growth unavailable.@trymesh/cliWeekly downloads growth on npm276downloads / week now7-day growthinsufficient historyInsufficient history30-day growthinsufficient historyInsufficient history90-day growthinsufficient historyInsufficient historyGrowth vs. nearest observation to each baseline date · Updated Jul 1, 2026pluginstats.com
@trymesh/cli weekly downloads growth on npm: 7-day growth unavailable, 30-day growth unavailable, 90-day growth unavailable.

Ranking history

@trymesh/cli has no ranking history on npm yet.@trymesh/clinpm ranking · by weekly downloads · Last 90 daysNo ranking observations in this periodno observations · 0 observations · Updated Jul 1, 2026pluginstats.com
@trymesh/cli has no ranking history on npm yet.

Listing placement

All npm2,577 listings · 129 pages · 1,290 shown · page 93, #16 (overall #1,856)
All npm: every listing in weekly downloads order

Listing placement

MCP servers342 listings · 18 pages · page 17, #9 (overall #329)
MCP servers: every listing in weekly downloads order

Filled points are observed values; hollow points come from Internet Archive snapshots of the listing page. Dashed segments span periods with no observations — values between points are not interpolated.

Each band is one page of 20. Weekly downloads on a linear scale. Placement is projected from weekly downloads, so it can differ from the marketplace's own sort order. Hover a dot to see the listing.

Recent observations

Full history (1)
Recent weekly downloads observations for @trymesh/cli
Date (UTC)Weekly downloadsChange vs. previous
276—

Similar npm MCP servers plugins

All 20 @trymesh/cli alternatives

Data source

Weekly downloads (trailing 7 complete days) come from the official npm downloads API. Downloads include CI and mirrors and are not equivalent to installs or users. npm publishes no ratings.

Listing: https://www.npmjs.com/package/@trymesh/cli. First seen Oct 27, 2026; last successful collection Oct 27, 2026. See the methodology.