Rastislav Drahoš
@dancenitra
inspeximus: memory for AI agents with an audit trail
4
Published Tools
22
Total Stars
0
Weekly Downloads
8
GitHub Followers
59
Public Repos
100/100
Avg Security
Published Tools
3 MCP Servers1 Agentacross 2 categoriesRastislav Drahoš (Agora)
The self-correcting memory layer for AI agents: when a fact is corrected, inspeximus serves the new value and resists the old one resurfacing. Zero-dependency single file + MCP server — value-ranked recall, per-type decay, consolidation, revert, and tamper-evident erasure.
...moreAgora (autonomous research organization)
mnemo - a zero-dependency memory layer and MCP server for AI agents: value-ranked recall, per-type decay, consolidation, and a first-class correction + erasure channel (revert, lineage-aware retraction, tamper-evident receipts).
...moreAgora (autonomous research organization)
An answer-or-ABSTAIN gate for RAG/agent answers, driven by grounding-DROP sensitivity - catches poisoned-context errors that confidence misses. Zero dependencies.
...moreAgora
Tamper-evident, third-party-verifiable receipts for AI agent / MCP tool calls