tweetindex
RU

Neon ✓

@neondatabase · Databricks · joined 23 Feb 2022

Backend for apps and agents built on Lakebase Postgres Free Plan: https://t.co/2oFkBiuLiV

20 528Followers
819Following
3 190Posts total
43.1KViews on collected posts

Последние посты

Large compute nodes in Lakebase Postgres now run up to 2× faster and with lower latency. We got here by increasing the shared buffers size and backing with huge pages. Details here, summary in thread: https://t.co/3IbhMLhFTr 1.1K views · 13 likes · 1 reposts · 1 replies Open on X →
@neondatabase the reversal is interesting: what changed your mind most, schema fidelity or the generated server’s handling of auth and errors? 19 views · 0 likes · 0 reposts · 0 replies Open on X →
Running on Neon 🤝 2K views · 16 likes · 0 reposts · 1 replies Open on X →
@neondatabase @arpit_bhayani right after your write up he he 199 views · 1 likes · 0 reposts · 1 replies Open on X →
@mastra @eve If you’re building agentic platforms or a personal agent, @neon/tools plus the Eve and Mastra adapters are for you. We share the full story in this blog post: https://t.co/Qu7A8WhrFq 335 views · 2 likes · 0 reposts · 0 replies Open on X →
@mastra We also built a native adapters at @neon/tools/eve for @eve agents to quickly take advantage of Neon Management API tools https://t.co/m3xCCsuvJ8
363 views · 2 likes · 0 reposts · 1 replies Open on X →
We also built a native adapter for @mastra @neon/tools/mastra exposes all Neon Management API tools for Mastra agents https://t.co/xyO4rnZFLz
3.7K views · 5 likes · 1 reposts · 1 replies Open on X →
That same catalog now sits behind Neon MCP. The hosted server now exposes 82 API tools from @neon/tools (68 of them new) next to the hand-written SQL, migration, and docs tools. https://t.co/6k445B7jM9 267 views · 4 likes · 0 reposts · 1 replies Open on X →
From this principle, we’ve built @neon/tools - It turns the Neon SDK into typed agent tools - Generated schemas stay in sync with the API - A reviewed layer adds polling and workflows - Tools wrap that layer - You pick the methods the agent needs https://t.co/eLLuj7BVpV
275 views · 4 likes · 0 reposts · 1 replies Open on X →
The thing is, we already invented something that solves this - SDKs. They give you the raw endpoints together with methods that bundle the common paths. And coding agents make building SDKs much cheaper than ever before (aside token costs, of course). Agent tools can work the 279 views · 4 likes · 0 reposts · 1 replies Open on X →
Our second objection (mapping every endpoint 1:1 to a tool) still stands. A REST call is still a poor agent tool. Progressive discovery can find every endpoint, it cannot turn those endpoints into a job. If the agent has to rediscover everything on every run, it burns tokens 309 views · 3 likes · 0 reposts · 2 replies Open on X →
Things have evolved since 2025. First, MCP clients do progressive tool discovery now - they search a catalog, inspect only the tools they need, then execute. This solves our first objection - or better said, selection and composition are now client problems 400 views · 5 likes · 0 reposts · 1 replies Open on X →
We were against the OpenAPI <> MCP server path for two reasons: 1. Tool definitions ate the context window: a large API meant hundreds of schemas in the prompt before the model even read the request 2. A REST operation is not a task: APIs are built around resources, but agents 647 views · 4 likes · 0 reposts · 3 replies Open on X →
Last year we thought that turning an OpenAPI spec into an MCP server was a shaky default. We’ve sort of changed our mind: https://t.co/w310DosHXz
5:55
12K views · 67 likes · 5 reposts · 4 replies Open on X →
Graph query support has just been pulled from Postgres 19 It was one of the release's most anticipated features, but too many design issues remained unresolved. We've updated our Postgres 19 coverage to reflect the change.https://t.co/FkW4xBoOMt https://t.co/z9qKA2QilX
7.9K views · 35 likes · 2 reposts · 1 replies Open on X →
.@fimoai 2.0 is LIVE! Make your AI-generated website editable and autonomous, so it gets better while you sleep 🧵 https://t.co/8xnCjR3i7v
0:30
7.9K views · 27 likes · 5 reposts · 1 replies Open on X →
New in Neon this week: - New models for AI Gateway: Fable 5.1, GLM 5.3 Flash, Grok 4.6, and OpenAI GPT-6 Astra landing soon - Neon Grok Bot plugin - More CLI updates: leaner neon init and neon env pull https://t.co/Yx82eaO9HR
0:08
5.4K views · 54 likes · 3 reposts · 5 replies Open on X →

На фоне аккаунтов своего размера

17 постов за последние 90 дней рядом с диапазоном 10K–100K подписчиков. ниже своих по обоим показателям — и по охвату, и по отклику.

Медианные просмотры400этот аккаунт924медиана для 10K–100K
Охват, %1.95%этот аккаунт3.62%медиана для 10K–100K
Вовлечённость, %1.00%этот аккаунт1.52%медиана для 10K–100K
ПоказательЭтот аккаунтМедиана для 10K–100KОтношение
Медианные просмотры на пост4009240.43×
Охват (просмотры ÷ подписчики)1.95%3.62%0.54×
Вовлечённость1.00%1.52%0.66×

Другие в этом диапазоне →   Сравнить с другим аккаунтом →   Как считаются эти ориентиры →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

12K8 Sep
647
400
309
279
275
267
3.7K
363
335
1999 Sep
2K
19
1.1K

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.64%8 Sep
1.08%
1.50%
1.62%
1.79%
1.82%
1.87%
0.19%
0.83%
0.60%
1.01%9 Sep
0.84%
0.00%
1.38%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes64.6%246 in total
Reposts4.5%17 in total
Replies6.6%25 in total
Bookmarks24.4%93 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Похожие аккаунты