Hacker News

Hi HN,

This is an agent framework I'm using myself for coding and various tasks. AI has gotten good enough that it can do a lot of tasks given simple but right tools which are composable.

These seven tools are most of what I need to get work done: read, write, diff, browse, command, ask, think.

Just looking to share and hope others find it useful, check it out at https://github.com/aperoc/toolkami.

Curious what are the main actions that is most useful for you?

Comments URL: https://news.ycombinator.com/item?id=43903472

Points: 1

# Comments: 2

Article URL: https://aitoggler.com/

Comments URL: https://news.ycombinator.com/item?id=43903468

Points: 1

# Comments: 0

Article URL: https://www.randompokemon.games

Comments URL: https://news.ycombinator.com/item?id=43903453

Points: 1

# Comments: 1

Article URL: https://www.tomshardware.com/pc-components/cpus/arrow-lake-die-shot-shows-off-the-details-of-intels-chiplet-based-design

Comments URL: https://news.ycombinator.com/item?id=43903420

Points: 2

# Comments: 0

Article URL: https://pietrasiak.com/in-a-democracy-you-should-have-two-votes-instead-of-one

Comments URL: https://news.ycombinator.com/item?id=43903417

Points: 2

# Comments: 1

We recently benchmarked AnuDB, a lightweight embedded database built on top of RocksDB, against SQLite on a Raspberry Pi. The performance difference, especially for parallel operations, was dramatic.

GitHub Links:

AnuDBBenchmark: https://github.com/hash-anu/AnuDBBenchmark

AnuDB (Core): https://github.com/hash-anu/AnuDB

Why Compare AnuDB and SQLite? SQLite is excellent for many embedded use cases — it’s simple, battle-tested, and extremely reliable. But it doesn't scale well when parallelism or concurrent writes are required.

AnuDB, built over RocksDB, offers better concurrency out of the box. We wanted to measure the practical differences using real benchmarks on a Raspberry Pi.

Benchmark Setup Platform: Raspberry Pi 2 (ARMv7)

Benchmarked operations: Insert, Query, Update, Delete, Parallel

AnuDB uses RocksDB and MsgPack serialization

SQLite uses raw data, with WAL mode enabled for fairness

Key Results Insert:

AnuDB: 448 ops/sec

SQLite: 838 ops/sec

Query:

AnuDB: 54 ops/sec

SQLite: 30 ops/sec

Update:

AnuDB: 408 ops/sec

SQLite: 600 ops/sec

Delete:

AnuDB: 555 ops/sec

SQLite: 1942 ops/sec

Parallel (10 threads):

AnuDB: 412 ops/sec

SQLite: 1.4 ops/sec (!)

In the parallel case, AnuDB was over 279x faster than SQLite.

Why the Huge Parallel Difference? SQLite, even with WAL mode, uses global database-level locks. It’s not designed for high-concurrency scenarios.

RocksDB (used in AnuDB) supports:

Fine-grained locking

Concurrent readers/writers

Better parallelism using LSM-tree architecture

This explains why AnuDB significantly outperforms SQLite under threaded workloads.

Try It Yourself Clone the repo:

git clone https://github.com/hash-anu/AnuDBBenchmark cd AnuDBBenchmark ./build.sh /path/to/AnuDB /path/to/sqlite ./benchmark

Results are saved to benchmark_results.csv.

When to Use AnuDB Use AnuDB if:

You need embedded storage with high concurrency

You’re dealing with telemetry, sensor data, or parallel workloads

You want something lightweight and faster than SQLite under load

Stick with SQLite if:

You need SQL compatibility

You value mature ecosystem/tooling

Feedback Welcome This is an early experiment. We’re actively developing AnuDB and would love feedback:

Is our benchmark fair?

Where could we optimize further?

Would this be useful in your embedded project?

Comments URL: https://news.ycombinator.com/item?id=43903414

Points: 2

# Comments: 0

Article URL: https://medium.com/google-cloud/building-ai-agents-with-google-adk-gemma-3-and-mcp-tools-28763a8f3c62

Comments URL: https://news.ycombinator.com/item?id=43903401

Points: 1

# Comments: 0

Article URL: https://ace-step.com

Comments URL: https://news.ycombinator.com/item?id=43903248

Points: 1

# Comments: 1

Article URL: https://github.com/reinaldmn/tenor20

Comments URL: https://news.ycombinator.com/item?id=43903234

Points: 1

# Comments: 0

Article URL: https://www.nextplatform.com/2025/05/02/amazon-says-it-can-embiggen-aws-past-multi-100-billion-with-ai/

Comments URL: https://news.ycombinator.com/item?id=43903231

Points: 1

# Comments: 0

Article URL: https://www.proventra-ai.com/blog/understanding-token-splitting-attacks-llms

Comments URL: https://news.ycombinator.com/item?id=43903230

Points: 2

# Comments: 0

Article URL: https://gowind.github.io/blog/thinkingincuda/

Comments URL: https://news.ycombinator.com/item?id=43903217

Points: 1

# Comments: 0

Article URL: https://www.ft.com/content/641f2cbc-e7d7-494d-b698-b794fd75f656

Comments URL: https://news.ycombinator.com/item?id=43903209

Points: 1

# Comments: 0

Article URL: https://github.com/andrewn6/fromthetransistor

Comments URL: https://news.ycombinator.com/item?id=43903206

Points: 2

# Comments: 0

Article URL: https://cacm.acm.org/blogcacm/what-ever-happened-toand-other-tech-history/

Comments URL: https://news.ycombinator.com/item?id=43903201

Points: 1

# Comments: 0

Article URL: https://aeturrell.com/blog/posts/introducing-smartrappy/

Comments URL: https://news.ycombinator.com/item?id=43903195

Points: 1

# Comments: 0

Article URL: https://maiobarbero.dev/articles/how-to-set-up-a-global-gitignore-with-git-config/

Comments URL: https://news.ycombinator.com/item?id=43903191

Points: 1

# Comments: 0

Article URL: https://ezebunandu.substack.com/p/the-kubernetes-gateway-api-through

Comments URL: https://news.ycombinator.com/item?id=43903175

Points: 1

# Comments: 0

Article URL: https://github.com/TheBoredTeam/boring.notch

Comments URL: https://news.ycombinator.com/item?id=43903167

Points: 2

# Comments: 0

Article URL: https://bitfieldconsulting.com/posts/things-fall-apart

Comments URL: https://news.ycombinator.com/item?id=43903164

Points: 1

# Comments: 0