AutoResearch
An open pipeline from ML research idea to reviewed, traceable evidence
Emerged finds new products worth a look, daily — what’s new today
For any problem with a measurable score and working baseline code, it runs parallel agent hypotheses and keeps evidence across generations instead of one-off tuning.
PRAXIST, from Sapient Intelligence, orchestrates parallel research agents on computer-executable problems with a measurable objective. Peers explore competing hypotheses, results are synthesised and carried forward across generations, and evidence is kept in durable lanes. It supports quality-diversity allocation, resume and replay, monitoring, and plugins for multiple runtimes and model providers. It installs with pip and is source-available under the Fair Source License, free below $1M annual revenue.
More like this
SoL-Pi
NVIDIA's extension that cuts coding-agent token use roughly in half
DeepSeek Harness
DeepSeek's open-source agent harness where every capability is a plugin
Drop7 Research
An open hunt for a million-point policy, playable as you read
no_human
Open-source agent that takes a ticket to a reviewed pull request, with proof
Whiteboard
A desktop canvas for reviewing what your coding agent actually built