<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: BohuTANG</title><link>https://news.ycombinator.com/user?id=BohuTANG</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 03 Jul 2026 12:59:46 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=BohuTANG" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: BendClaw – Distributed AgentOS Written in Rust]]></title><description><![CDATA[
<p>Hi HN, we're open-sourcing BendClaw today -- the distributed AgentOS behind Evot.AI.<p>The problem: one shared agent maxes out fast. Separate agents per person means everyone starts from zero. We wanted the third option -- distributed compute with shared knowledge.<p>BendClaw is a runtime where multiple agents run in parallel, each on its own node, but all connected to one shared data layer. When one agent learns something, every other agent has it on the next run. No prompt engineering, no manual handoff.<p>What's inside:<p>- *Shared memory* -- all agents read and write to the same knowledge base. Context, learnings, history, fully connected.
- *Cluster dispatch* -- agents fan out subtasks across nodes and collect results. Local and cloud nodes in one cluster.
- *Self-evolving* -- every run automatically extracts knowledge and injects it into future runs.
- *Trace and audit* -- every operation recorded. Who did what, which tools fired, what came back. All queryable.
- *Secret-safe* -- secrets vault-isolated, never exposed to the LLM. Approval gates on sensitive actions.
- *Token-aware* -- per-agent budgets with proactive alerts before anything runs out.
- *100+ integrations* -- custom tools via Skills: write a description, point it at a script, done.<p>Rust, Apache-2.0. Hosted platform at <a href="https://evot.ai" rel="nofollow">https://evot.ai</a> if you want to skip self-hosting.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47427436">https://news.ycombinator.com/item?id=47427436</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 18 Mar 2026 16:01:56 +0000</pubDate><link>https://github.com/EvotAI/bendclaw</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=47427436</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47427436</guid></item><item><title><![CDATA[New comment by BohuTANG in "Snowtree: Review-Driven Safe AI Coding"]]></title><description><![CDATA[
<p>Hey everyone, I'm excited to open-source Snowtree: my tool for safe AI coding!<p>Team up with AI like Claude or Codex in your IDE—stay in control with isolated sessions, easy reviews, and snapshot saves. No chaos, just smarter workflows.</p>
]]></description><pubDate>Sat, 10 Jan 2026 16:57:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46567405</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=46567405</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46567405</guid></item><item><title><![CDATA[Snowtree: Review-Driven Safe AI Coding]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.bohutang.me/2026/01/10/snowtree-review-driven-safe-ai-coding/">https://www.bohutang.me/2026/01/10/snowtree-review-driven-safe-ai-coding/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46567404">https://news.ycombinator.com/item?id=46567404</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 10 Jan 2026 16:57:19 +0000</pubDate><link>https://www.bohutang.me/2026/01/10/snowtree-review-driven-safe-ai-coding/</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=46567404</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46567404</guid></item><item><title><![CDATA[New comment by BohuTANG in "Databricks acquires Neon"]]></title><description><![CDATA[
<p>Yes, Databend's metadata service (<a href="https://github.com/databendlabs/databend/tree/main/src/meta">https://github.com/databendlabs/databend/tree/main/src/meta</a>) also uses a Raft implementation written in Rust: <a href="https://github.com/databendlabs/openraft">https://github.com/databendlabs/openraft</a>.<p>We've been running OpenRaft in production for several years now and have found it to be quite stable. It's designed as a generic, feature-complete Raft library that handles the complexities of distributed consensus well. If you're looking for a mature Rust Raft implementation, it's definitely worth considering.</p>
]]></description><pubDate>Fri, 23 May 2025 00:26:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=44068574</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=44068574</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44068574</guid></item><item><title><![CDATA[New comment by BohuTANG in "Databricks acquires Neon"]]></title><description><![CDATA[
<p>Neon (open-source alternative to Aurora) is 73.6% Rust. Databend (open-source Snowflake alternative) is even more Rust-heavy at 97.2%.<p>Interesting trend - modern serverless databases choosing Rust for its memory safety, performance predictability. Makes sense for systems where reliability and efficiency are non-negotiable.</p>
]]></description><pubDate>Thu, 15 May 2025 00:47:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=43990716</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=43990716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43990716</guid></item><item><title><![CDATA[New comment by BohuTANG in "Show HN: Query Fast - Lightweight data analytics with AI"]]></title><description><![CDATA[
<p>BendSQL is a cli tool.<p>I suggest to use the drivers list here: <a href="https://docs.databend.com/guides/sql-clients/developers/" rel="nofollow">https://docs.databend.com/guides/sql-clients/developers/</a></p>
]]></description><pubDate>Tue, 14 Jan 2025 11:28:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=42696036</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=42696036</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42696036</guid></item><item><title><![CDATA[New comment by BohuTANG in "Show HN: Query Fast - Lightweight data analytics with AI"]]></title><description><![CDATA[
<p>Thanks, sverg! From my experience, query-fast is a better product than many other AI-to-SQL solutions. I'm really looking forward to this product.</p>
]]></description><pubDate>Thu, 09 Jan 2025 04:25:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=42641625</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=42641625</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42641625</guid></item><item><title><![CDATA[New comment by BohuTANG in "Show HN: Query Fast - Lightweight data analytics with AI"]]></title><description><![CDATA[
<p>Interesting, I tried query-fast and it's impressive! It would be great to add Databend as a data source—it's a cost-efficient alternative to Snowflake:
<a href="https://www.databend.com/" rel="nofollow">https://www.databend.com/</a></p>
]]></description><pubDate>Thu, 09 Jan 2025 04:23:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=42641603</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=42641603</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42641603</guid></item><item><title><![CDATA[New comment by BohuTANG in "Why Choose Rust as Your Development Language"]]></title><description><![CDATA[
<p>Rust is great for building databases because it ensures memory safety, avoids garbage collection, and prevents memory leaks and data races. Databend is a prime example—it's one of the largest database projects written in Rust, with over 476,000 lines of code developed from scratch over the past three years. While Rust isn't as widely adopted as some other languages, its use in projects like Databend demonstrates its potential for creating high-performance, reliable systems.</p>
]]></description><pubDate>Mon, 30 Dec 2024 01:11:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=42545339</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=42545339</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42545339</guid></item><item><title><![CDATA[UUID(v7)]]></title><description><![CDATA[
<p>Article URL: <a href="https://docs.databend.com/sql/sql-functions/uuid-functions/gen-random-uuid">https://docs.databend.com/sql/sql-functions/uuid-functions/gen-random-uuid</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42134649">https://news.ycombinator.com/item?id=42134649</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 14 Nov 2024 10:01:22 +0000</pubDate><link>https://docs.databend.com/sql/sql-functions/uuid-functions/gen-random-uuid</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=42134649</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42134649</guid></item><item><title><![CDATA[New comment by BohuTANG in "A new JSON data type for ClickHouse"]]></title><description><![CDATA[
<p>Yes, reliable data ingestion often involves Kafka, which can feel complex. An alternative is the transactional COPY INTO approach used by platforms like Snowflake and Databend. This command supports "exactly-once" ingestion, ensuring data is fully loaded or not at all, without requiring message queues or extra infrastructure.<p><a href="https://docs.databend.com/sql/sql-commands/dml/dml-copy-into-table#copyoptions" rel="nofollow">https://docs.databend.com/sql/sql-commands/dml/dml-copy-into...</a></p>
]]></description><pubDate>Sun, 27 Oct 2024 01:08:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=41959069</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41959069</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41959069</guid></item><item><title><![CDATA[New comment by BohuTANG in "DuckDB vs. Snowflake vs. Databricks"]]></title><description><![CDATA[
<p>Looking forward to adding Databend, the open-source alternative to Snowflake:
<a href="https://github.com/databendlabs/databend/issues/13059">https://github.com/databendlabs/databend/issues/13059</a></p>
]]></description><pubDate>Sat, 19 Oct 2024 03:43:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=41885489</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41885489</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41885489</guid></item><item><title><![CDATA[New comment by BohuTANG in "How Do People Use Snowflake and Redshift?"]]></title><description><![CDATA[
<p>The snowset[1] in the post is quite dated—it’s based on data from February 21 to March 7, 2018, which doesn't reflect current usage trends. Many users find Snowflake too expensive now, especially with the added costs of ETL. With the rise of open-source alternatives like Databend[2], users have more options when considering a move away from Snowflake.<p>[1]snowset: <a href="https://github.com/resource-disaggregation/snowset">https://github.com/resource-disaggregation/snowset</a><p>[2]Databend: <a href="https://github.com/datafuselabs/databend">https://github.com/datafuselabs/databend</a></p>
]]></description><pubDate>Tue, 24 Sep 2024 03:36:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=41632927</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41632927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41632927</guid></item><item><title><![CDATA[New comment by BohuTANG in "Top 5 Snowflake Alternatives for Cost-Effective Data Warehousing"]]></title><description><![CDATA[
<p>Check out Databend, an open-source alternative to Snowflake with 90%+ product and syntax similarity (almost no migration cost). It’s cost-effective and powerful.<p>GitHub: <a href="https://github.com/datafuselabs/databend/issues/13059">https://github.com/datafuselabs/databend/issues/13059</a><p>Comparison: <a href="https://www.databend.com/comparison" rel="nofollow">https://www.databend.com/comparison</a></p>
]]></description><pubDate>Sat, 07 Sep 2024 00:49:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=41470782</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41470782</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41470782</guid></item><item><title><![CDATA[The Easy Way to Master JSON in SQL: Databend's jq Function]]></title><description><![CDATA[
<p>Article URL: <a href="https://docs.databend.com/sql/sql-functions/semi-structured-functions/jq">https://docs.databend.com/sql/sql-functions/semi-structured-functions/jq</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41353805">https://news.ycombinator.com/item?id=41353805</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 26 Aug 2024 03:39:55 +0000</pubDate><link>https://docs.databend.com/sql/sql-functions/semi-structured-functions/jq</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41353805</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41353805</guid></item><item><title><![CDATA[New comment by BohuTANG in "TIL: Versions of UUID and when to use them"]]></title><description><![CDATA[
<p>UUID v7's timestamp is a game-changer for Databend. We're using it to quickly locate metadata files on AWS S3 by timestamp, making operations like vacuuming much faster.<p>PR: <a href="https://github.com/datafuselabs/databend/pull/16049">https://github.com/datafuselabs/databend/pull/16049</a></p>
]]></description><pubDate>Mon, 26 Aug 2024 03:33:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=41353787</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=41353787</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41353787</guid></item><item><title><![CDATA[New comment by BohuTANG in "FoundationDB at Snowflake: Architecture and Internals (2021) [video]"]]></title><description><![CDATA[
<p>Databend is a cutting-edge alternative to Snowflake, offering cost-effective and straightforward solutions for large-scale analytics. It utilizes a lightweight meta service instead of the resource-intensive FoundationDB and employs OpenRaft for replication and high availability.<p>- Databend: <a href="https://github.com/datafuselabs/databend">https://github.com/datafuselabs/databend</a><p>- OpenRaft: <a href="https://github.com/datafuselabs/openraft">https://github.com/datafuselabs/openraft</a></p>
]]></description><pubDate>Wed, 17 Jul 2024 07:33:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=40983394</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=40983394</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40983394</guid></item><item><title><![CDATA[New comment by BohuTANG in "Building a dynamic lib plugin system for Rust"]]></title><description><![CDATA[
<p>Great post!
The sandboxing and pluggability of UDFs are key. Databend now supports Python, JavaScript, and WebAssembly to simplify data processing.<p>[1] Embedded UDFs: <a href="https://docs.databend.com/guides/query/udf#embedded-udfs" rel="nofollow">https://docs.databend.com/guides/query/udf#embedded-udfs</a><p>[2] <a href="https://x.com/DatabendLabs/status/1796830863344463884" rel="nofollow">https://x.com/DatabendLabs/status/1796830863344463884</a></p>
]]></description><pubDate>Mon, 03 Jun 2024 03:41:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=40559137</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=40559137</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40559137</guid></item><item><title><![CDATA[New comment by BohuTANG in "Show HN: Turn CSV Files into SQL Statements for Quick Database Transfers"]]></title><description><![CDATA[
<p>Yeah.
The insert statement fails when dealing with larger datasets, and the parser incurs significant overhead.
The most efficient method is to use the COPY INTO command like in Databend[1] or Snowflake[2] for bulk data loading.<p>[1] Databend: <a href="https://docs.databend.com/guides/load-data/load-semistructured/load-csv" rel="nofollow">https://docs.databend.com/guides/load-data/load-semistructur...</a><p>[2] Snowflake: <a href="https://docs.snowflake.com/en/sql-reference/sql/copy-into-table" rel="nofollow">https://docs.snowflake.com/en/sql-reference/sql/copy-into-ta...</a><p>[3] Data Ingestion Benchmark: <a href="https://docs.databend.com/guides/benchmark/data-ingest" rel="nofollow">https://docs.databend.com/guides/benchmark/data-ingest</a></p>
]]></description><pubDate>Wed, 29 May 2024 01:44:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=40507452</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=40507452</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40507452</guid></item><item><title><![CDATA[New comment by BohuTANG in "Show HN: Hacker Search – A semantic search engine for Hacker News"]]></title><description><![CDATA[
<p>Nice work.
It's recommended to start with a keyword search (including titles, comments, and the keyword itself) before using an LLM-based search. For example, if I search for 'databend' on <a href="https://hackersearch.net/search?q=databend&period=last-3-years" rel="nofollow">https://hackersearch.net/search?q=databend&period=last-3-yea...</a>, it defaults to an LLM-based search. However, I prefer using a simple keyword search instead.</p>
]]></description><pubDate>Mon, 06 May 2024 03:08:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=40270799</link><dc:creator>BohuTANG</dc:creator><comments>https://news.ycombinator.com/item?id=40270799</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40270799</guid></item></channel></rss>