Attributed mentions
164
Across all collected Hacker News results
Discussion intelligence
A source-linked Hacker News monitor for the tracked company graph. These are attributable public discussions—not sentiment, endorsements, or unverified company facts.
Attributed mentions
164
Across all collected Hacker News results
Companies represented
12
Exact-name monitor matches only
Collection source
Hacker News
Latest new record seen Today
Source-backed records
Showing 101–120 of 164 matching discussions
Namecoach/Euphonia | Founding Voice AI Engineer (part-time, path to CAIO) | SF or Remote | REMOTE | Contract / Part-time, ~$30-120/hr by seniority, potentially converting to FT Namecoach has spent 10 years building the largest verified pronunciation dataset of its kind: ~2M self-recorded name pronunciations, plus a large corpus of human-verified phonetic spellings. We're now building Euphonia ( https://euphonia.namecoach.ai/ ), a provider-neutral middleware layer that makes any TTS engine pronounce names, acronyms, and other out-of-vocabulary terms correctly. The new wave of TTS (models from OpenAI, ElevenLabs, etc) sounds great but gives you almost no phoneme-level control, so it gets lots of names and words wrong and you can't easily fix it. We sit in front…
For my current purposes, I need a speech-to-text model/API to also emit word-level timestamps - for now, that makes ElevenLabs's Scribe v2 the best multiplatform, multi-language choice though it does look like this SpeechAnalyzer API provides them (although only for English).
Hi HN folks ! I am the author of AVA, a self hosted AI Voice Agent that plugs into Asterisk/Freepbx so you own all the aspects of an AI Voice agent in your own infrastructure. It uses Asterisk native Audiosocket/RTP with python engine to run STT,LLM and TTS loop. The project support several full providers openai, gemini, grok, elevenlabs out of the box and also provides options to build custom pipelines by choosing different stt tts and llm. It also supports full local agent if you have a GPU with 25GB RAM which enables realtime conversation along with tool calling. I started this as a hobby project last year when I started exploring voice agents and every saw every Saas tried to lock you in their eco system. Since then project has taken off and a lot of asterisk people started …
Location: Ahmedabad, India Remote: Yes Willing to relocate: No Technologies: Python, Django, DRF, FastAPI, PostgreSQL, LangChain, RAG pipelines, MCP servers, agentic AI workflows, Stripe integration Résumé/CV: https://www.linkedin.com/in/himanshu-more-dev/ ; https://todo-smoky-alpha.vercel.app/ Email: hmore7978@gmail.com Backend/AI engineer with production experience building RAG pipelines, custom MCP servers, and agentic workflows. Recently built an AI Todo Assistant (FastAPI + LangChain + MCP + Gemini Flash) and a multi-tenant SaaS app with real-time location tracking. Open to freelance/contract work, quick turnaround on RAG/agent integration tasks.
Sounds like a very cool project. I often use the ElevenLabs app/extension to listen to articles, but I would love to have a local option to do this. I'm on Windows though, so I look forward to your future updates.
Location: Skopje, North Macedonia Remote: Yes (CET timezone, comfortable with EU/US overlap) Willing to relocate: No Technologies: Python (FastAPI, LangChain, LangGraph), RAG systems (Neo4j GraphRAG, pgvector), LLM integration (OpenAI, Anthropic, local Llama via Ollama/vLLM), OCR pipelines (Google Vision, PaddleOCR), MLOps (MLflow, GitHub Actions CI/CD, Docker, AWS ECS/Fargate, ECR), classical ML (scikit-learn, regression and classification models), SQL/PostgreSQL, evaluation tooling (DeepEval, LangSmith), Frontend (React), Mobile apps (React-Native). Résumé/CV: https://github.com/hamzaarifi98/mycv Email: hamzaa.arifii@gmail.com Portfolio: https://github.com/hamzaarifi98
Location: Austin, TX Remote: Yes Willing to relocate: No Technologies: • Programming languages: Go, Python (FastAPI, Flask), Node.js, Java (Spring Boot), PHP. • Backend architecture: microservices, REST APIs, event-driven design, idempotency, concurrency. • Cloud and DevOps: Amazon Web Services (AWS) S3, Lambda, EC2; Kubernetes; Docker; CI/CD pipelines. • Data stores: PostgreSQL, MySQL, Redis, Memcached. • Messaging: Apache Kafka, RabbitMQ, Google Pub/Sub. • AI and machine learning: retrieval-augmented generation (RAG), vector databases (Pinecone, Weaviate), large language model (LLM) APIs. • Observability: Prometheus, Grafana, Datadog, Elasticsearch Logstash Kibana (ELK), distributed tracing. • APIs and security: gRPC, GraphQL, OAuth 2, JSON Web Tokens (JWT), role-based access …
Location: Austin, TX Remote: Yes Willing to relocate: No Technologies: • Programming languages: Go, Python (FastAPI, Flask), Node.js, Java (Spring Boot), PHP. • Backend architecture: microservices, REST APIs, event-driven design, idempotency, concurrency. • Cloud and DevOps: Amazon Web Services (AWS) S3, Lambda, EC2; Kubernetes; Docker; CI/CD pipelines. • Data stores: PostgreSQL, MySQL, Redis, Memcached. • Messaging: Apache Kafka, RabbitMQ, Google Pub/Sub. • AI and machine learning: retrieval-augmented generation (RAG), vector databases (Pinecone, Weaviate), large language model (LLM) APIs. • Observability: Prometheus, Grafana, Datadog, Elasticsearch Logstash Kibana (ELK), distributed tracing. • APIs and security: gRPC, GraphQL, OAuth 2, JSON Web Tokens (JWT), role-based access …
Data engineer with 3.5 years, built PySpark pipelines processing billions of records daily, dimensional models, and Unity Catalog governance serving 10+ teams. Recently hands-on with LLM systems: RAG on Bedrock, multi-agent POCs, MLflow tracing. Looking for data/AI engineering or forward-deployed roles,. Location: Austin, TX Remote: Yes (US) Willing to relocate: No Technologies: Python, SQL, PySpark, Databricks, Delta Lake, dbt, Airflow, AWS (S3, Glue, Bedrock, EMR), Snowflake, Redshift, Kafka, Docker, Terraform | AI: RAG, LangChain, CrewAI, MLflow, LLM orchestration Résumé/CV: github.com/analondhe Email: anaghaalondhe7@gmail.com
Location: Tashkent, Uzbekistan Remote: Yes Willing to relocate: Yes Technologies: Python, FastAPI, LangChain, RAG (pgvector, FAISS), classical ML (XGBoost, LightGBM, CatBoost, scikit-learn), React, Next.js, TypeScript, Flutter, PHP, MySQL/Postgres, Supabase, Docker Résumé/CV: https://drive.google.com/file/d/12O_duaC2O47aFvF_7OoSc97XEP9... GitHub: https://github.com/ioa2205 LinkedIn: https://www.linkedin.com/in/ibodullo Email: ioa22052005@gmail.com Full-stack AI engineer — production RAG systems, LLM integration, and full-stack apps/platforms built from scratch. Shipped an ERP voice AI agent across four production platforms, an AI-powered ATS (TezHR, live), and an EdTech platform (FastAPI/Supabase/Flutter&…
Rowboat markets itself as "local-first," but if you look in the actual codebase, transcription is Deepgram cloud, voice is ElevenLabs, analytics is PostHog, and the LLM is a cloud API.
Fair list: 1. True - no OS-level container today. The constraint is approval gating: consequential actions surface as a permission ask before they run (a separate supervisor LLM flags anything outside your intent). 2. True today. We'd deprioritized generic IMAP (drafts-on-thread is unreliable cross-provider), but you're the third person in this thread to raise it, so we'll scope it properly. 3/4/5. Today: Deepgram for STT, ElevenLabs for TTS, Exa for search. At least for search we supported more providers earlier (e.g. Brave) and found the assistant's skills degrade when they can't lean on provider-specific capabilities, like Exa's granular search. So we trimmed and went deep on a few. Feel free to raise a GitHub issue with what you want us to support and we'll do our best.
Location: New York, NY Remote: Yes Willing to relocate: Yes Technologies: Python, PHP, TypeScript, AI Agent, RAG, Prompt-Engineering, LangChain, LangGraph, React, Vue.js Résumé/CV: https://drive.google.com/file/d/1lycaftoYFy-Y-wmNJ70zUbliS3s... Email: kevintom9605@gmail.com Senior AI & Data Engineer with 8+ years of experience designing scalable data platforms, machine learning solutions, and Generative AI applications. Experienced in building enterprise data pipelines, cloud-native AI systems, Retrieval-Augmented Generation (RAG) platforms, agentic AI workflows, and production ML infrastructure on AWS. Strong background in Python, SQL, distributed data processing, vector databases, LLM orchestration, and MLOps. Passionate about delivering reliable AI solutio…
Location: Knoxville, TN 37932 Remote: Yes Willing to relocate: Yes Technologies: Python, TypeScript, React, Next.js, Node.js, FastAPI, Django, PostgreSQL, MongoDB, Redis, GCP, Azure, AWS, Docker, Kubernetes, OpenAI, Claude, Vertex AI, LangChain, RAG, MCP, CI/CD Resume: https://drive.google.com/file/d/1OpfHwNWTTY3FYWZpeatTP0IkNmr... Email: patrick35353@outlook.com
Easy to send one’s clipboard to Microsoft Azure and have their DragonHD voices read the text, say with Keyboard Maestro (or presumably Alfred, Raycast, etc.). Should work with selected text too. You’d definitely get to pay for it, not what I consider cheap. (“$15 per 1M characters”) But IMO just about best-in-class (maybe ElevenLabs has a voice I’d like even better).
Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices. I do wish there were better support for SSML, as well as deeper documentation of how to influence inflection in-line, but the default does well with standard emphasis (e.g. putting asterisks around text elements). Both asks are getting outside the zone of reasonable asks for this sort of distribution, though, and I remain incredibly grateful for the quality of what hexgrad and nazdridoy have put out in the world.
Hi HN, I’m Dale. I’m building Polygres with my twin brother and a longtime friend who is a decade older than us lol. Polygres is an all in one Postgres-based database that combines relational data, graph traversal, vector search, full-text search, and reranking over the same source-of-truth data. We built this because we kept seeing devs building RAG or agent systems having to sync the same data across several stores: Postgres for application data, Qdrant or Pinecone for vectors, Neo4j for graph traversal, and then a lot of glue code to keep everything consistent. That adds operational complexity, stale-index problems, and awkward retrieval logic. Polygres is our attempt to keep more of that inside Postgres. You can insert and update data with normal SQL, represent relationships as a grap…
Hi HN, I’m Dale. I’m building Polygres with my twin brother and a longtime friend who is a decade older than us lol. Polygres is an all in one Postgres-based database that combines relational data, graph traversal, vector search, full-text search, and reranking over the same source-of-truth data. We built this because we kept seeing devs building RAG or agent systems having to sync the same data across several stores: Postgres for application data, Qdrant or Pinecone for vectors, Neo4j for graph traversal, and then a lot of glue code to keep everything consistent. That adds operational complexity, stale-index problems, and awkward retrieval logic. Polygres is our attempt to keep more of that inside Postgres. You can insert and update data with normal SQL, represent relationships as a grap…
Hey HN! I'm Diego. I've been extensively using Qdrant for hybrid search, but there's no standard way to track and manage schema migrations. I've used alembic in the past for relational databases, so I decided to develop something similar for Qdrant: revector. You write declarative YAML migrations, commit them next to your code, and apply or roll them back with a single static binary. Repo: https://github.com/diegoglozano/revector Docs: https://diegoglozano.github.io/revector/ Thanks for taking a look, happy to hear your feedback!
so this is really cool and I think could be the missing piece for something I wanted to build, I found this awhile back and using https://github.com/npiesco/absurder-sql you could keep the entire raw corpus in browser (persisted via IndexedDB/SQLite)...then you could generate + cache embeddings on demand with Ternlight (instead of pre-indexing everything i.e., https://weaviate.io/blog/chunking-strategies-for-rag ). then this opens up the door for Reciprocal Rank Fusion (RRF) aka hybrid retrieval where you combine FTS5/BM25 from the native SQLite plues the semantic search using from TernLight!
Methodology: HN Search returns recent public items matching a monitored company name. AIIStack stores a short normalized excerpt and the original link, deduplicates by company/provider/item ID, and creates an activity signal only after a threshold of newly observed records. Review the original discussion before making a decision.