Contributions
1671 contributions in 2026 JanFebMarAprMayJunJulAug
MonWedFri
Merged Pull Requests
Latest 20 across 5 repositories- fix(ontology): coalesce normalized property collisions semantica-agi/semantica ·
- fix(ontology): retain data properties for normalized class names semantica-agi/semantica ·
- fix(agent): implement webhook trace polling infiniflow/ragflow ·
- fix(ontology): resolve relationship endpoint types for domain and range semantica-agi/semantica ·
- fix(agent): propagate webhook terminal states infiniflow/ragflow ·
- fix(agent): redact internal terminal errors infiniflow/ragflow ·
- fix(agent): surface cancellation terminal state infiniflow/ragflow ·
- fix(kg): validate entity_id aliases semantica-agi/semantica ·
- fix(kg): keep relationship endpoint aliases in sync semantica-agi/semantica ·
- feat(agent): support OpenAI-compatible responses infiniflow/ragflow ·
- fix(kg): preserve entity_id aliases during entity merging semantica-agi/semantica ·
- fix(kg): honor exact entity resolution semantica-agi/semantica ·
- fix(kg): preserve isolated nodes in graph analytics semantica-agi/semantica ·
- fix(kg): make k-shortest path search side-effect free semantica-agi/semantica ·
- fix(kg): remap relationship endpoints after entity resolution semantica-agi/semantica ·
- fix(core): treat empty tool chunk ids as missing in merge langchain-ai/langchain ·
- fix(openai): detect codex models for responses api preference langchain-ai/langchain ·
- fix(langchain): normalize raw schemas in middleware response_format override langchain-ai/langchain ·
- feat(backend): cover webhook ingress URL route Significant-Gravitas/AutoGPT ·
- [Misc] Fix typo: seperator -> separator in flashmla_sparse.py vllm-project/vllm ·
Pinned
MarketPulse
Financial News AI Analysis Notification Service
pad
Stop hunting panes. Run your AI workflow from one place.
langchain
The agent engineering platform.
opencode
The open source coding agent.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs