repoGitHubTrust 82 · PrimaryPublished yesterdayLive · 21h ago
bug-ops/zeph
A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Implements
Covers
Related across the graph
paperSelf-rewarding agents that retrace failurespaperSWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction TestsnewsOpenAI reveals its first AI processor: JalapeñopaperCan Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool UsenewsOpenAI to acquire Ona
