Claude returned ```json blocks 14% of the time. Here is the Rust crate I wish I had earlier.
via DEV Community: rust (author: Mukunda Rao Katta)
via DEV Community: rust (author: Mukunda Rao Katta)
Telegraph
Claude returned ```json blocks 14% of the time. Here is the …
I had a system prompt that ended with: Reply with only a JSON object. Do not include code fences. Do not include explanation. That should be enough. It is not. Over a week of structured-output calls (12,400 of them, mostly Claude Sonnet 4.5 and 4.7), I logged…
Our retry loop made an outage worse. The circuit breaker stopped the cascade.
via DEV Community: rust (author: Mukunda Rao Katta)
via DEV Community: rust (author: Mukunda Rao Katta)
Telegraph
Our retry loop made an outage worse. The circuit breaker sto…
A few weeks back there was a 22-minute window where Anthropic returned a high rate of 5xx responses. Not a full outage. Degraded. Our agent service had a retry policy that backed off and tried again on 5xx. With six workers and a shared retry budget that…
The Day Our Latency Shot Up When the Runtime Decided to GC
via DEV Community: rust (author: pretty ncube)
via DEV Community: rust (author: pretty ncube)
Telegraph
The Day Our Latency Shot Up When the Runtime Decided to GC
The Problem We Were Actually Solving We needed a way to move money out of countries where PayPal, Stripe, and Gumroad had no footprint. Our micro-payment layer already integrated with local aggregators—EasyPaisa in Pakistan, bKash in Bangladesh, Flutterwave…
Chat With Your Documents Using Garudust Agent — No Vector Database Required
via DEV Community: rust (author: Garudust)
via DEV Community: rust (author: Garudust)
Telegraph
Chat With Your Documents Using Garudust Agent — No Vector Da…
Most RAG tutorials start the same way: "First, install a vector database…" Then come the embedding models, the chunking strategies, the similarity thresholds. By the time you can ask a question about a PDF, you've deployed three services and written 200 lines…
React 19 Hydration Errors & Rust Async Traits: Two Deep Dives
via DEV Community: rust (author: gunturss24)
via DEV Community: rust (author: gunturss24)
Telegraph
React 19 Hydration Errors & Rust Async Traits: Two Deep Dives
React 19 Hydration Mismatch — Root Cause & Fix If you've upgraded to React 19 and started seeing hydration errors like: Error: Hydration failed because the initial UI does not match what was rendered on the server. Here's the actual root cause and how to…
Cron & Scheduled Tasks in Garudust Agent — Autonomous Agents That Run Without You
via DEV Community: rust (author: Garudust)
via DEV Community: rust (author: Garudust)
Telegraph
Cron & Scheduled Tasks in Garudust Agent — Autonomous Agents…
Most AI agents wait. They sit idle until a human types something, respond, then go back to waiting. Garudust Agent can be different. With garudust-cron, you schedule tasks using standard cron syntax — the agent wakes up, runs a full LLM loop with all its…
Rust Concurrency: Threads, Channels, Mutex & Sync (Part 4)
via DEV Community: rust (author: mihir mohapatra)
via DEV Community: rust (author: mihir mohapatra)
Telegraph
Rust Concurrency: Threads, Channels, Mutex & Sync (Part 4)
This is Part 4 of the Core Rust Concepts series. Part 1 — Ownership, Borrowing, Lifetimes, Traits, Result/Option, Pattern Matching Part 2 — Closures, Iterators, Generics, Enums, Smart Pointers, Async/Await Part 3 — Macros, Modules, Testing, Unsafe Rust, FFI…
Show HN: Rmux – A programmable terminal multiplexer with a Playwright-style SDK!
via DEV Community: rust (author: Mariano Gobea Alcoba)
via DEV Community: rust (author: Mariano Gobea Alcoba)
Telegraph
Show HN: Rmux – A programmable terminal multiplexer with a P…
Rmux: A Programmable Terminal Multiplexer with an SDK-Driven Automation Model The landscape of terminal multiplexers has long been dominated by tools like tmux and screen, which provide robust session management, window splitting, and pane organization. These…
I Still Have Nightmares About Our Treasure Hunt Engine Deployment
via DEV Community: rust (author: pretty ncube)
via DEV Community: rust (author: pretty ncube)
Telegraph
I Still Have Nightmares About Our Treasure Hunt Engine Deplo…
The Problem We Were Actually Solving I was part of the team that operated the Veltrix system, a complex piece of software that we used to manage and analyze large datasets for our clients. One of the key components of this system was the Treasure Hunt Engine…
Rust Developer Seeks Feedback on G-Code Simulator with TUI/GUI After Overcoming Terminal Rendering Challenges
via DEV Community: rust (author: Sergey Boyarchuk)
via DEV Community: rust (author: Sergey Boyarchuk)
Telegraph
Rust Developer Seeks Feedback on G-Code Simulator with TUI/G…
Introduction In the realm of manufacturing, G-code serves as the backbone for CNC machines, dictating precise movements that shape raw materials into finished products. A Rust developer has recently tackled the challenge of simulating these instructions with…
I Survived the Treasure Hunt Engine Debacle by Questioning Everything I Knew About Event Architecture
via DEV Community: rust (author: pretty ncube)
via DEV Community: rust (author: pretty ncube)
Telegraph
I Survived the Treasure Hunt Engine Debacle by Questioning E…
The Problem We Were Actually Solving I still remember the day our team decided to implement the Treasure Hunt Engine, a complex event-driven system designed to handle thousands of concurrent users. As the lead systems engineer, I was responsible for ensuring…
I Was Asked to Add a Simple Classifier to a Website. Then I Saw the 250 MB Download.
via DEV Community: rust (author: Pavel)
via DEV Community: rust (author: Pavel)
Telegraph
I Was Asked to Add a Simple Classifier to a Website. Then I …
A client asked me for a simple thing. Not ChatGPT. Not an agent. Not a multimodal assistant that can explain invoices, generate React components, and write poetry in three languages. Just a small classifier embedded into a website. The job sounded boring…
Six Months of AI-Assisted Software Development: A Critical Evaluation of Vibe Coding, Agentic IDEs, and Real Engineering
via DEV Community: rust (author: Onur GUZEL)
via DEV Community: rust (author: Onur GUZEL)
Telegraph
Six Months of AI-Assisted Software Development: A Critical E…
Six Months of AI-Assisted Software Development: A Critical Evaluation of Vibe Coding, Agentic IDEs, and Real Engineering Introduction For roughly the past six months, I have been working intensively with large language models, agentic IDEs, and AI-assisted…
BoxAgnts Runtime (3) — WebAssembly: A Better Sandbox for AI Agents
via DEV Community: rust (author: Guyoung Studio)
via DEV Community: rust (author: Guyoung Studio)
Telegraph
BoxAgnts Runtime (3) — WebAssembly: A Better Sandbox for AI …
AI agents are increasingly moving beyond text generation. Modern agent systems can execute code, manipulate files, browse the web, call APIs, manage infrastructure, and coordinate distributed tasks. Once agents begin interacting with real environments, execution…
Stop shipping a 1990s C library to compute planets. Xalen is the pure-Rust, Apache-2.0 replacement for Swiss Ephemeris.
via DEV Community: rust (author: Xalen Technologies)
via DEV Community: rust (author: Xalen Technologies)
Telegraph
Stop shipping a 1990s C library to compute planets. Xalen is…
Stop shipping a 1990s C library to compute planets. Xalen is the pure-Rust, Apache-2.0 replacement for Swiss Ephemeris. If your app does astrology, you already know the dependency. Swiss Ephemeris: a C library from the 1990s, a folder of binary .se1 data…
Query Markdown as a Database with mq-db: SQL, mq, and Interval Indexes
via DEV Community: rust (author: Takahiro Sato)
via DEV Community: rust (author: Takahiro Sato)
Telegraph
Query Markdown as a Database with mq-db: SQL, mq, and Interv…
Managing large collections of Markdown documents (documentation sites, knowledge bases, notes) often means resorting to a messy combination of grep and regex. mq-db takes a different approach: it parses every Markdown element into a typed block, builds interval…
Web Developer Travis McCracken on Rust vs Go in Production APIs
via DEV Community: rust (author: Travis McCracken Web Developer)
via DEV Community: rust (author: Travis McCracken Web Developer)
Telegraph
Web Developer Travis McCracken on Rust vs Go in Production A…
Why Backend Development with Rust and Go Is My Passion: Insights from Web Developer Travis McCracken As a web developer deeply immersed in backend technologies, I often find myself exploring the strengths and nuances of languages like Rust and Go. My journey…
I built a local-first AI memory layer for LLMs in Rust (no cloud, no API keys)
Every LLM app has the same problem — the model forgets everything between
conversations. Cloud solutions like Mem0 exist but they send your data
to their servers. I built mnemo to solve this locally.
What it does
mnemo runs as a sidecar process next to your app. You POST text to it,
it extracts named entities and relationships using a local LLM (Ollama),
builds a persistent knowledge graph, and injects relevant context back
into your prompts automatically.
The stack
● Rust — core engine, 4 crates (mnemo-core, mnemo-api, mnemo-cli, mnemo-bench)
● SQLite + WAL mode — persistent storage, survives restarts
● petgraph — in-memory knowledge graph with BFS traversal
● Axum — REST API sidecar any app can call
● Ollama — fully local LLM, zero API costs
Fully free by default
Works with OpenAI or Anthropic too if you bring your own key.
Python SDK
Numbers
● 122 Rust tests, 21 Python SDK tests
● Sub-millisecond entity lookup
● ~4ms full retrieval pipeline (debug build)
Links
GitHub: https://github.com/zaydmulani09/mnemo
Would love feedback, especially on the retrieval scoring and graph
traversal approach.
via DEV Community: rust (author: Zayd Mulani)
Every LLM app has the same problem — the model forgets everything between
conversations. Cloud solutions like Mem0 exist but they send your data
to their servers. I built mnemo to solve this locally.
What it does
mnemo runs as a sidecar process next to your app. You POST text to it,
it extracts named entities and relationships using a local LLM (Ollama),
builds a persistent knowledge graph, and injects relevant context back
into your prompts automatically.
The stack
● Rust — core engine, 4 crates (mnemo-core, mnemo-api, mnemo-cli, mnemo-bench)
● SQLite + WAL mode — persistent storage, survives restarts
● petgraph — in-memory knowledge graph with BFS traversal
● Axum — REST API sidecar any app can call
● Ollama — fully local LLM, zero API costs
Fully free by default
docker compose up -d
docker exec mnemo-ollama ollama pull llama3
curl http://localhost:8080/health
Works with OpenAI or Anthropic too if you bring your own key.
Python SDK
from mnemo import MnemoClient
client = MnemoClient()
client.ingest("I'm building a Rust vector database called vecdb")
print(client.get_context("what am I working on?"))
Numbers
● 122 Rust tests, 21 Python SDK tests
● Sub-millisecond entity lookup
● ~4ms full retrieval pipeline (debug build)
Links
GitHub: https://github.com/zaydmulani09/mnemo
Would love feedback, especially on the retrieval scoring and graph
traversal approach.
via DEV Community: rust (author: Zayd Mulani)