Open Issues Need Help
View All on GitHub Golden dataset: a fixed set of layered cases to measure whether an API change helps or hurts 20 days ago
help wanted benchmarks
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Rust
#agent-memory#ai-agents#aider#bitemporal#claude-code#cline#codex#coding-agents#cozodb#cursor#gemini-cli#github-copilot#knowledge-graph#llm#mcp#memory#model-context-protocol#opencode#rag#rust
Research: pick a benchmark that measures "agentic memory", not RAG about 2 months ago
help wanted research benchmarks
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Rust
#agent-memory#ai-agents#aider#bitemporal#claude-code#cline#codex#coding-agents#cozodb#cursor#gemini-cli#github-copilot#knowledge-graph#llm#mcp#memory#model-context-protocol#opencode#rag#rust
help wanted research benchmarks
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Rust
#agent-memory#ai-agents#aider#bitemporal#claude-code#cline#codex#coding-agents#cozodb#cursor#gemini-cli#github-copilot#knowledge-graph#llm#mcp#memory#model-context-protocol#opencode#rag#rust
Run kaeru on the chosen agentic-memory benchmark 3 months ago
help wanted research benchmarks
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Rust
#agent-memory#ai-agents#aider#bitemporal#claude-code#cline#codex#coding-agents#cozodb#cursor#gemini-cli#github-copilot#knowledge-graph#llm#mcp#memory#model-context-protocol#opencode#rag#rust