PROJECT · Research
caura-ai/caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Research Intelligence Feed
Read the latest filtered projects and GitHub-backed demand signals here. To receive updates in an RSS app, copy the XML feed address below.
RESEARCH RSS SUBSCRIPTION URL
Follow every refresh
A web browser may display the XML feed as code. That is normal—the address is designed to be pasted into an RSS reader.
13Research feed entries
PROJECT · Research
deepset-ai/haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
PROJECT · Research
bytedance/deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
DEMAND SIGNAL · Research
Support dynamic tool addition/removal after agent creation and in middleware
Demand evidence from langchain-ai/langchain: 18 comments and 16 positive reactions.
DEMAND SIGNAL · Research
Doesn't honour pydantic model field datatype and randomly throws `langchain_core.exceptions.OutputParserException`
Demand evidence from langchain-ai/langchain: 29 comments and 5 positive reactions.
DEMAND SIGNAL · Research
Feature: GuardrailProvider interface for automated tool-call policy enforcement
Demand evidence from deepset-ai/haystack: 12 comments and 0 positive reactions.
DEMAND SIGNAL · Research
Proposal: Transaction Protocol for idempotent, auditable agent pipelines
Demand evidence from deepset-ai/haystack: 7 comments and 0 positive reactions.
DEMAND SIGNAL · Research
Feature: Post-RAG FactChecker Pipeline Component & Header-Aware Document Splitter
Demand evidence from deepset-ai/haystack: 9 comments and 0 positive reactions.
DEMAND SIGNAL · Research
feat(clients): map HTTP 429 to a dedicated RateLimitError with retry_after
Demand evidence from caura-ai/caura: 2 comments and 0 positive reactions.
DEMAND SIGNAL · Research
The batch method from ChatModels and all the Runnables does not really support the OpenAI batch API.
Demand evidence from langchain-ai/langchain: 17 comments and 37 positive reactions.
PROJECT · Research
langchain-ai/langchain
The agent engineering platform.
PROJECT · Research
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
PROJECT · Research
thedotmack/claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More