@Context7AI
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
Up-to-date documentation for LLMs and AI code editors. A project by @upstash team
San Francisco
Joined April 2025
- Tweets365
- Following7
- Followers8.7K
- Likes866
Software factory is the next level of coding with AI. You're the CEO, agents do the work.
Watch @leonvz build one you can copy. Agents pick up tasks, write code and ship, each in its own Upstash Box sandbox.
youtu.be/AsvzMlLyQ38
Introducing Context7 Search:
a grounding API for coding agents.
One GET request, get the docs snippets.
Unlike web search:
• Official docs, managed by library owners
• Scanned for prompt injection and malware
• Fast and token efficient
Blog:
upstash.com/blog/context7-se…
Upstash now supports Redis Arrays.
Not a list. Index = address, not position.
- O(1) random access (lists walk O(N))
- Sparse slots cost nothing
- Delete doesn't shift
- ARRING: ring buffer in one command, 2x RPUSH+LTRIM
upstash.com/blog/redis-array…
We benchmarked Docs7 vs Mintlify on Upstash docs.
Docs7 won 33 of 34 Pagespeed comparisons.
Page load on mobile: 3.3s vs 9.7s
Static HTML at build time, served from Cloudflare. Raw data in the post.
upstash.com/blog/docs7-vs-mi…
Docs7 👏
shipped docs for StackTaste on docs7, works great!
docs.stacktaste.com
We tested Jev against the models we use inside Context7's parsing pipeline (Gemini Flash, DeepSeek).
5 classification tasks. Results:
- 3 ties: query relevance, duplicate detection, website suitability
- 1 win: page classification — 85% vs 56%
- 1 loss: crawl-root selection — 27% vs 93%
- 10-170x faster, 3-20x cheaper
Tagging a single page: Jev wins.
Reasoning about a whole site's structure: it doesn't.
Crawl-root selection: given a URL + site nav, pick which section to crawl.
Query relevance: is the user's question about this library or something else.
Duplicate detection: are two snippets the same example.
Website suitability: is this site technical docs worth indexing.
Page classification: does this doc page have code, API ref, or info.
Context7 now indexes DeepWiki pages too.
Before: "the lifecycle of a user message in Chainlit" → nothing useful, because no docs page says it.
After: real answer, pulled from the repo's DeepWiki.
Your agent can now ask how things work.
Every Context7 doc is scanned before your agent sees it
Your AI agent reads docs. Docs can carry prompt injections.
Context7 scans every doc before indexing. A custom classifier flags injection attempts and malware patterns.
context7.com/docs/security/d…
Someone asked Context7 about EVAL on Upstash Redis REST API.
Our docs didn't cover it. Docs7 agents noticed the gap, wrote the docs, opened a PR. We reviewed and merged it.
Docs that fix themselves when users hit a gap. That's the goal.
github.com/upstash/docs/pull…
Box is now part of the Upstash MCP.
Any agent gets a remote sandbox, your GitHub repos, a browser, file storage. On the subscription you already pay for.
We tried it: 12 PRs across 4 repos from one Claude chat message. Nothing built on my laptop.
upstash.com/blog/turn-any-ag…
we are not great at hype. stable growth is peaceful.
I don't see enougn hype around the @Context7AI mcp. It's a staple in every project I work on. Thanks for the good work guys
Every Docs7 site serves WebMCP out of the box. No setup.
And the dashboard shows what AI agents are actually searching for in your docs.
Doc7 shows you which AI agents read your docs.
Every request from ChatGPT, Claude, Meta, etc. is a row: agent, page, country, time.
Screenshot is from Upstash docs, right now. Turns out agents read a lot of ratelimit and QStash pages.
we paid mintlify $1000+/month just for AI chat usage.
we built Docs7. no usage fees for AI docs chat, included in the $200 pro plan.
context7.com/docs7
we've learned the hard way that usage pricing needs to be predictable and results oriented
so we’re moving to fixed, outcome-based pricing
you pay for completed outcomes, and we take on the underlying compute variability
this means that
→ 100% of costs can be forecasted in advance
→ ~96% of teams will spend less on the AI assistant
→ self-updating content costs ~70% less on average
Context7 retweeted
if you want ai agents to recommend your product, you should start with SEO
new big number @Context7AI
Context7 is now an OpenCode plugin.
opencode plugin @upstash/context7-opencode
MCP server + a skill that auto-triggers doc lookups. One command, no config.
context7.com/docs/clients/op…
