krapcys1-maker

krapcys1-maker/nullius

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

10 good first / help-wanted issues · TypeScript · last activity Aug 30, 2026

1 stars 0 forks 1 watchers TypeScript MIT License
ai-agents epistemics evidence llm multi-agent research-automation
View on GitHub
10 Open Issues Need Help Last updated: Aug 30, 2026

Open Issues Need Help

View All on GitHub
The largest file in a repository is always skipped, and it is the likeliest place for the mechanism about 2 months ago
help wanted good first issue recall
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
Code inspection is invisible to the report, and to the model that concludes no candidate exists about 2 months ago
help wanted good first issue
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
A run can lose every memory record it wrote and report "Retained 18/18" about 2 months ago
help wanted infrastructure silent-failure
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
Recall reports "the bank had nothing" when it was the resolver that dropped everything about 2 months ago
help wanted recall silent-failure
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
The inspection depth field records the verdict, not the depth — and is false every time it is set about 2 months ago
help wanted evidence-inflation silent-failure
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
Recall finds mechanism families reliably and specific systems unreliably about 2 months ago
help wanted recall
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
Relevance gate admits documents that share only mechanism vocabulary about 2 months ago
help wanted relevance-gate
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
A successful code inspection does not raise the evidence class of the hypothesis it supports about 2 months ago
help wanted evidence-inflation
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
The query-leak audit misses 2 of 12 known leaked strings about 2 months ago
help wanted good first issue test-infrastructure
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation
Replay recorded model responses, the way provider responses are already replayed about 2 months ago
help wanted test-infrastructure
krapcys1-maker/nullius
1

An autonomous research agent that must show its evidence. Field notes on the one bug that kept reappearing: confusing 'we did not find it' with 'it is not there'.

TypeScript
#ai-agents#epistemics#evidence#llm#multi-agent#research-automation