pldpld

We were building voice agents across multiple platforms and had no way to regression test them. Prompt tweak on one node would silently break three other conversation paths. So we built voicetest.

It imports your agent config from any supported platform into a universal IR (AgentGraph), then runs autonomous multi-turn conversation simulations against it. A simulator LLM plays the caller, your agent graph handles the routing, and an LLM judge scores transcripts against success criteria. Also supports deterministic rule tests for compliance stuff, PII leakage, required disclosures, forbidden phrases.

Write tests once and they work across platforms. Import from Retell, export to VAPI, run the same test suite. Also does format conversion between platforms if you're migrating.

Has interfaces for CLI (CI/CD), web UI, REST API, and a TUI. Results go into DuckDB so you can query them. Uses LiteLLM via DSPy so it works w/whatever provider you want

https://github.com/voicetestdev/voicetest

https://voicetest.dev/

https://github.com/voicetestdev/voicetest

- test harness for voice agents. - multi platform formats (Retell, VAPI, Bland, LiveKit) compile down to a unified AgentGraph IR - import from one platform, test locally, export to another - use litellm, DSPY to config models, if on a subscription use claudecode as a runner to avoid API call charges - metric judges produce continuous 0-1 scores instead of binary pass/fail since a 0.65 and a 0.35 both fail a 0.7 threshold but represent very different agent behaviors. - persist to DuckDB for querying across test history - adding auto-healing graph mutations where failed tests propose structural + prompt changes to the agent graph and validate against a regression suite

Wrote up the architecture here https://peet.ldee.org/general/2026/02/03/testing-voice-ai-ag...

Thank you! It came out of that feeling of I need to use this, but I don't want to have to manage it or have to learn the details more than once. Now I find myself using it daily in my workflow, not having to worry about the extra worktree folders saves enough time to make it worthwhile

Ona | Burlington, Vermont & Nairobi, onsite / remote | Senior Software Engineers, Frontend Engineers | full time | https://www.ona.io/jobs.html

Our global health platform is used on smartphones by community health workers around the world to track and monitor their patients offline and on. Our data and ML platforms analyze patient risk, coordinate humanitarian projects, and manage Covid-19 tracking and messaging campaigns. We were named one of the “50 Most Genius Companies” by TIME magazine and have partnerships with the World Health Organization, the Bill and Melinda Gates Foundation, UNICEF, the United Nations Development Program, the World Food Program, and others.

References: https://blog.ona.io/news/2018/11/16/path-bid-story.html, https://blog.ona.io/canopy/covid19/2020/09/01/how-we-launche...

Our Global Health team stack is Android / Java / Postgres / React

Our Data Platform team stack is Django / Clojure / ClojureScript React (om -> reagent)

Our ML team stack is Beam / NiFi / Kafka / SciPy + Jupyter (prototyping) / Superset

We have full-time positions available, as well as fellowships and other opportunities.

https://ona.io/jobs.html

jobs+hn@ona.io

Ona | Nairobi, remote | Fellowships / Software Dev / PM | full time | https://www.ona.io/jobs.html

Named one of the “50 Most Genius Companies” by TIME magazine, we are a social enterprise building technology products that improve access to essential, life-saving services. We are funded by the World Health Organization, the Bill and Melinda Gates Foundation, UNICEF, the United Nations Development Program, the World Food Program, and others.

Ona's GIT fellowship is a 12-week, Nairobi-based engagement pairing experienced software engineers with a global health or humanitarian open source project.

Our Global Health mobile team stack is Android / Java / Postgres / React

Our Data Platform team stack is Django / Clojure / ClojureScript React (om -> reagent)

Our ML team stack is NiFi / Kafka / SciPy + Jupyter (prototyping) / Superset

We have full-time positions available, as well as fellowships and other opportunities to contribute, https://ona.io/jobs.html

Ona | Software Engineer | Nairobi, Kenya & New York, NY | Full Time | Onsite

We're looking for developers who want to build foundational data systems that drive change. Our team has worked on projects that record the social infrastructure of entire countries, tally the winners of national elections, reduce infant mortality, and decrease the spread of malaria. We build software that solves real problems and you will too. We were named a TIME Magazine Genius Company of 2018.

Global health stack

* Android, Java, Postgres

Data platform stack

* Python, Clojure, ClojureScript, PostGIS

Data warehouse stack

* NiFi, Kafka, Druid, Superset, React, Redux

Learn about our recent projects and what it's like to work at Ona, https://blog.ona.io/

Join us by applying here, https://ona.io/jobs/sw_eng.html Additional roles listed here, https://ona.io/jobs.html

Ona | Software Engineer | Nairobi, Kenya | Full Time | Onsite

We're looking for developers who want to build foundational data systems that drive change. Our team has worked on projects that record the social infrastructure of entire countries, tally the winners of national elections, and reduce infant mortality. We build software that solves real problems and you will too.

Global health stack

* Android, Java, Postgres

Data platform stack

* Python, Clojure, ClojureScript, PostGIS

Data warehouse stack

* NiFi, Kafka, Druid, Superset, React, Redux

Learn about our recent projects and what it's like to work at Ona, https://blog.ona.io/

Join us by applying here, https://ona.io/jobs/sw_eng.html

Kobo is based off of onadata, https://github.com/onaio/onadata (which is actively maintained) which was in turn the continuation of formhub (which is no longer maintained).

See this readme https://github.com/kobotoolbox/kobocat for reference

Ona | Jakarta, Nairobi, New York, Washington DC | Multiple Positions | ONSITE | Full-time | https://ona.io/

We're hiring senior Android and Java engineers for a new Jakarta office focused on building out the OpenSRP frontline healthcare application.

We build data management platforms and mobile health applications used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the Ebola crisis in West Africa, counted votes during a Libyan election, is surveying national infrastructure in post-earthquake Nepal, and is scheduling vaccines in Bangladesh, Indonesia, Kenya, Pakistan, Zambia, and soon expanding to more countries per our collaboration with the WHO.

The stack you'll work with depends on the project, active stacks include: Clojure/Script + Om, Django + PostGIS, Android + CouchDB, React, and a Data engineering stack with NiFi + HDFS + Kafka + Druid + Superset, details here, https://blog.ona.io/general/2017/08/30/streaming-ona-data-wi...

In a technical interview we'll ask systems architecture questions, then we'll write and extend code together, then we'll describe our culture and see if it would be a good fit. We're currently hiring interaction designers and senior engineers, https://ona.io/jobs.html, jobs@ona.io

Ona | New York, Washington DC, Nairobi | Multiple Positions | ONSITE | Full-time | https://ona.io/

We build data management platforms and tablet health applications used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the Ebola crisis in West Africa, counted votes during a Libyan election, is surveying national infrastructure in post-earthquake Nepal, and is scheduling vaccines in Bangladesh, Indonesia, Keny, Pakistan, Zambia, and soon expanding to more countries per our collaboration with the WHO.

The stack you'll work with depends on the project, active stacks include: Clojure/Script + Om, Django + PostGIS, Tomcat + CouchDB, React, and a Data engineering stack with NiFi + HDFS + Kafka + Druid + Superset, details here, https://blog.ona.io/general/2017/08/30/streaming-ona-data-wi...

In a technical interview we'll ask systems architecture questions, then we'll write and extend code together, then we'll describe our culture and see if it would be a good fit. We're currently hiring interaction designers and senior engineers, https://ona.io/jobs.html, jobs@ona.io

Ona (https://ona.io/) | Nairobi, Kenya | Senior Software Engineer | ONSITE | Full-time

We build a data management platform and tablet health application used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the ebola crisis in West Africa, counted votes during a Libyan election, is surveying national infrastructure post-earthquake in Nepal, and scheduling vaccines in Bangladesh, Indonesia, Pakistan, Indonesia, Zambia, and other places soon.

The stack you'll work with depends on the project, active stacks: Clojure/Script + Om, Django + PostGIS, Tomcat + CouchDB, see our FOSS at https://github.com/onaio/ and our 2016 roundup https://blog.ona.io/general/2016/12/30/year-in-tech-at-ona.h...

In the interview we'll ask tech and background questions to get to know each other, then we'll write and extend code together, https://ona.io/jobs/senior_sw_eng.html jobs+swe@ona.io@ona.io

Ona (https://ona.io/) | Nairobi, Kenya | Senior Software Engineer / Project Managers | ONSITE | Full-time

We build a data management platform and tablet health application used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the ebola crisis in West Africa, counted votes during a Libyan election, is surveying national infrastructure post-earthquake in Nepal, and scheduling vaccines in Bangladesh, Indonesia, Pakistan, Indonesia, Zambia, and other places soon.

The stack you'll work with depends on the project, active stacks: Clojure/Script + Om, Django + PostGIS, Tomcat + CouchDB, see our FOSS at https://github.com/onaio/ and our 2016 roundup https://blog.ona.io/general/2016/12/30/year-in-tech-at-ona.h....

In the interview we'll ask tech and background questions to get to know each other, then we'll write and extend code together, https://ona.io/jobs/senior_sw_eng_android.html, https://ona.io/jobs/project_manager.html jobs+swe+opensrp@ona.io@ona.io, jobs+project-manager@ona.io

Ona (https://ona.io/) | Nairobi, Kenya | Senior Android/Java Engineer | ONSITE | Full-time

We build a data management platform and tablet health application used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the ebola crisis in West Africa, counted votes during a Libyan election, is surveying national infrastructure post-earthquake in Nepal, and scheduling vaccines in Bangladesh, Indonesia, Pakistan, Indonesia, Zambia, and other places soon.

The stack you'll work with depends on the project, active stacks: Clojure/Script + Om, Django + PostGIS, Tomcat + CouchDB, see our FOSS at https://github.com/onaio/ and our 2016 roundup https://blog.ona.io/general/2016/12/30/year-in-tech-at-ona.h...

In the interview we'll ask tech and background questions to get to know each other, then we'll write and extend code together, https://ona.io/jobs/senior_sw_eng_android.html, jobs+swe+opensrp@ona.io@ona.io

Ideally having worked remotely, held an intership before, or something equivalent. But I remember applying for my early dev jobs when every posting wanted 3 years experience. We don't exclude anyone by default, no hard requirements, a PR is is the best way to get our attention https://github.com/onaio.

No need for iOS at this time, but we do need Android developers. Most of our work is deployed or working with organizations and individuals in lower-income environments, so the priority is on Android. We'd like to develop equivalents of our Android apps for iOS but it's not justifiable at this stage.

Remote is OK for the intern position as well, but we'd be expecting a bit more experience for a remote intern.

Ona (https://ona.io/) | New York City | Engineering Interns, Senior Engineers | Remote OK | Full-time

We build a data management platform and tablet health application used globally to improve child and maternal health, governance, agriculture, access to infrastructure, and government accountability. E.g. our software routed patients during the ebola crisis in West Africa, counted votes during a Libyan election, and is surveying national infrastructure post-earthquake in Nepal.

The stack you'll work with depends on the project, active stacks: Clojure/Script + Om, Django + PostGIS, Tomcat + CouchDB, see our FOSS at https://github.com/onaio/ and our 2016 roundup https://blog.ona.io/general/2016/12/30/year-in-tech-at-ona.h...

In the interview we'll ask tech and employment questions to get to know each other, then we'll write and extend code together, https://ona.io/jobs/sw_eng_intern.html, jobs@ona.io

You can! https://github.com/clojure/clojurescript, https://github.com/swannodette/om

Former SEL team member here, SEL also produces a lot of open source code, for background and inspiration checkout their github projects, https://github.com/SEL-columbia

Hi alphakappa, we had used an image because the original did not have a permanent home, but now it does. The image is now replaced with an iframe, http://bamboo.io/docs/examples.html#an-interactive-map-of-th..., also here is the map site http://sel-columbia.github.io/egypt-2012/

Hi sz4kerto, writer of bamboo here, I agree that the name's clashing with other tools' names makes it a poor choice. Because bamboo was a prototype and initially for internal use we did not do a lot of name research and were not aware of those other tools when we chose the name, maybe we will rename it once it hits beta.

We chose the name bamboo because it uses pandas as the processing engine.

Hi lerchmo, writer of bamboo here, the data is stored column-wise in mongo, aggregates are calculated with pandas, hence the name of the library. This is a prototype and using pandas let us quickly perform many common statistical operations. In a future version we plan to decouple the processing engine so we can push calculations into the db layer as appropriate.

use another OS, http://www.cyanogenmod.org/blog/cyanogenmod-will-never-have-...

Sep Kamvar has done a significant amount of research addressing precisely the problems you describe. The conclusion being that (in non-pathological cases, which would likely include the case you vaguely describe) one can design network architectures using reputation mechanisms such that malicious peers are found and routed around. See http://kamvar.org/publications, specifically "Numerical Algorithms for Personalized Search in Large-Scale Self-Organizing Information Networks" (the first Book) esp. Chapter 9, I highly recommend it.

It is time to build a clone of this project.

"As a business you can monitor all of your input costs in real time. You can monitor by region, industry, specific supplier. The search engine will also have advanced statistical features to give you directional probabilities of pricing in the short term. Instead of a rigid, just-in-time inventory approach to your inputs, your program will alert you when the likelihood of waiting one more week to buy, or buying one week early, will give you a better price."

by Kevin Price, original here, http://www.zerohedge.com/article/why-mit-not-willing-unleash...

Where's some source code for this?

There are related papers here, http://ccrg.cs.memphis.edu/papers.html, but I'd like to see some code.

This is reminiscent of Funk2, http://www.funk2.org/about/, it would be interesting to compare and contrast these approaches.

Why is title bar there? I was hoping they'd push the tabs up into the title bar like Chrome and give us more screen space.