The reliability layer for AI coding agents.
vexp.dev SourceAI Models & Agents / Agent Tools & MCP Servers
- Monthly visits
- 19.9K
- Down19.3%MoMSep 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- $29/mo
- Higher than 72% of peersNiche median $19/mo
- Launched
- 9mo ago
- 2026-02-22 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- SaaS is officially dead 🥀 Marc's Datafast has lost $2k in MRR and ~50 subs were cancelled in last 30 days. It's falling at a rate of ~$60/day. > It’s just a script tag and a dashboard. Switching takes 10 minutes. > No real data lock-in.
@ahmedgagan11 · 2026-11-06 · 150 likes · 2 reposts · 52.1K views
- @lucas_martinic Profile: https://www.ship-or-die.com/u/lucas-martinic 回复原帖 @shipordie_: Treasure hit the deck. @lucas_martinic just received $100 for Polyfork. 💰 Total revenue: $21K 📈 Last 30 days: $5,795
@shipordie_ · 2026-11-06 · 0 likes · 0 reposts · 23 views
Vexp launched on Product HuntLaunch
Local-first context engine for AI coding agents
Mar 31 · 8mo agoSource
Vexp launched on Product HuntLaunch
Cut AI coding costs 58% with pre-indexed codebase context
Mar 12 · 8mo agoSource
Vexp launched on Show HN (2 pts)Launch
Focused input cuts LLM output tokens by 63% bench on CC with FastAPI — I built an MCP server (vexp) that pre-indexes a codebase into a dependency graph and serves only relevant code to AI coding agents. While…
Mar 3 · 9mo agoSource
Vexp launched on Show HN (4 pts · 2 comments)Launch
58% cost by replacing file reads with a dependency graph on AI Coding — I got tired of watching Claude Code read entire files when it needed one function. Built an MCP server that pre-computes a dependency grap…
Mar 2 · 9mo agoSource
Vexp launched on Show HN (1 pts)Launch
Vexp – Your AI coding agent forgets everything. Mine doesn't — I built vexp because AI coding agents have two expensive problems: they waste tokens reading irrelevant code, and they forget everything b…
Feb 24 · 9mo agoSource
Third-party reviews & case dossiers
Acquisition breakdowns, engineer reviews & open-source metrics- Post excerpt:
- I've been building vexp for the past months to solve a problem that kept bugging me: AI coding agents waste most of their context window reading code they don't need. The problem When you ask Claude Code or Cursor to fix a bug, they typically grep around, cat a bunch of files, and dump thousands of lines into the context. Most of it is irrelevant. You burn t
- Post excerpt:
- I built vexp to solve two problems I kept hitting with AI coding agents (Claude Code, Cursor, etc.): 1. Token waste: agents read entire files linearly to understand a codebase. On a medium TypeScript project, a single query was consuming ~18k tokens of context when only ~2.4k were relevant. 2. Session amnesia: every new session starts from zero. The agent re
- Post excerpt:
- I built vexp because AI coding agents have two expensive problems: they waste tokens reading irrelevant code, and they forget everything between sessions. The token problem: agents read entire files linearly to build context. On a medium TypeScript project, a single query was consuming ~18k tokens — most of it irrelevant. vexp builds a dependency graph from
- Post excerpt:
- I got tired of watching Claude Code read entire files when it needed one function. Built an MCP server that pre-computes a dependency graph with tree-sitter and serves only the relevant code nodes to the agent. Ran a proper benchmark to see if it actually matters. Setup: FastAPI codebase (800 Python files), Claude Sonnet 4.6, 7 tasks (bug fixes, features, re
- Post excerpt:
- I built an MCP server (vexp) that pre-indexes a codebase into a dependency graph and serves only relevant code to AI coding agents. While benchmarking it, I found something I wasn't looking for. The expected results were straightforward: less input context → lower cost, fewer tool calls → faster. But the output token reduction was the surprise. Benchmark: 7
Open Source & Agent Ecosystem
- GitHub Stars
- Public repo
- Forks
- —
- License
- See repository
- Primary language
- —
- Ecosystem & integrations:
- Claude CodeContinue.devAntigravityFriday CodeClaudeVS Code
- Exposed tool capabilities:
- Repository ContextAgent MemoryContext searchImpact analysisMemory recallDependency graph
Traffic sources
Traffic breakdown
Channels
- Direct40%
- Organic Search33%
- Referrals10%
- Social6%
- Other10%
Countries
- United States16%
- Vietnam15%
- India10%
- Brazil10%
- Germany9%
Search
Domain authority —Domain registered 2026-02-21
| Keyword | Monthly volume |
|---|---|
| vexp | 520 |
| is 1m context better than 256k but compacted | 310 |
| node js what is it claude | 220 |
| shared context between codex claude | 150 |
| in claude code what is the optimal context size for best results analysis with graphs | 120 |
Traffic data: Vaneform
Pricing
Trial: None · 1 paid tier ($29) · Observed 2026-11-03 · Source page
Entry price $29/mo, Higher than 72% of peers; “Agent Tools & MCP Servers” median is $19/mo.View pricing benchmark
Pages & changes
Key pages
Weekly snapshotsChanges
No pricing, plan, or positioning changes detected since tracking started.
Design
Dark Developer (Dark canvas, balanced density) featuring centered headline + cta layout and product ui screenshot / component visuals.
First-screen preview · click to zoom
First-screen pitch & conversion flow
“The reliability layer for AI coding agents.”
Centered Headline + CTA hero structure paired with download app / install extension CTA and user count, rating, or key metrics.
Conversion path: Centered Headline + CTA + Product UI Screenshot / Component → Download App / Install Extension · Trust bar: User Count, Rating, or Key Metrics
- Category Positioning Anchor
- Large Hero Product Shot
- Code & Terminal
- Metrics Strip
Palette · click to copy
- Typography
- 8.0
- Color & Contrast
- 8.0
- Layout & Spacing
- 8.0
- Craft & Polish
- 8.0
- Distinctiveness
- 7.0
Structure
- Fonts
- Inter / Geist Mono
- Hero layout
- Centered Headline + CTA
- Primary visual
- Product UI Screenshot / Component
- Conversion CTA
- Download App / Install Extension
- Social proof
- User Count, Rating, or Key Metrics
- Navigation
- Floating Pill Nav
- Theme & density
- Dark · Balanced
- Corners & depth
- Medium Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Dark Developer (with Minimal Monochrome)
Deep dark surfaces, monospace typography, terminal/code snippets, and high-precision borders.
## Design Tokens
```css
:root {
--background: #0a0c11;
--surface: #10131b;
--foreground: #eef1f8;
--muted-foreground: #929bb2;
--accent: #13d7a1;
--radius: 8px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-mono: "Geist Mono", ui-monospace, monospace;
}
```
Color area ratio: Background #0A0C11 (~77%) · Surface #10131B (~11%) · Text #EEF1F8 (~5%) · Muted Text #929BB2 (~6%) · Accent #13D7A1 (~1%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.
## Layout & Conversion Structure
- Hero layout: Centered Headline + CTA
- Navigation: Floating Pill Nav
- Theme & density: Dark · Balanced
- Border radius & elevation: Medium Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Product UI Screenshot / Component
- Conversion CTA: Download App / Install Extension · Trust bar uses User Count, Rating, or Key Metrics
- Headline hook: Category Positioning Anchor
- Hero components: Large Hero Product Shot, Code & Terminal, Metrics Strip
- Spatial layout notes: Centered Headline + CTA hero structure paired with download app / install extension CTA and user count, rating, or key metrics.
- Visual summary: Dark Developer (Dark canvas, balanced density) featuring centered headline + cta layout and product ui screenshot / component visuals.
## Avoid
- Warm pastel backgrounds
- Playful cartoon illustrations
- Oversized pill buttons everywhere
Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.
Questions & evidence
- How much does Vexp cost?
- Starter: Unknown; Pro: Unknown; Team: $29/mo. Observed 2026-11-03. Check the source for current billing terms, usage limits and taxes.Source
- How much website traffic does Vexp get?
- Vaneform estimates 19.9K website visits in 2026-09. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
- What is Vexp and what platforms does it support?
- Vexp is catalogued under Agent Tools & MCP Servers: The reliability layer for AI coding agents.. Supported platforms: CLI / SDK.
- Is Vexp open source?
- Vexp has a public repository (https://github.com/Vexp-ai/swe-bench-pro-opus-5-vexp) with its source repository published.Source
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.
| Product | Entry price | Visits | Revenue |
|---|---|---|---|
| ComposioGive your AI secure access to 1,500+ apps in minutes | $29/mo | 2.8M | Undisclosed |
| Browser UseBrowser agents and cloud browsers. | — | 1.2M | Undisclosed |
| Desktop CommanderUse your computerfrom chat | $20/mo | 1M | Undisclosed |
| CapMonster CloudAI-Powered CAPTCHA Solver | $1.3/mo | 862.3K | Undisclosed |
| CapafyDomain Expert AI Agent Store | — | 796.8K | Undisclosed |
| AIPRMYour Cheat Code for ChatGPT | $10/mo | 708.9K | Undisclosed |