Research
47 tools across 4 categories tagged with “research”
agents
(17)AI Deep Research Agent
Autonomous agent that conducts comprehensive multi-source research investigations
AI Journalist Agent
Autonomous agent that researches topics and writes structured news articles
OpenHands
Open-source AI software agent platform, formerly OpenDevin
GPT Researcher
Autonomous deep research agent producing 2K+ word reports from 20+ sources — 26K+ stars
SWE-agent
Princeton's autonomous agent for resolving GitHub issues and software engineering benchmarks
AdsMind
Physics-grounded multi-agent system for catalyst surface adsorption discovery
AREX
Recursively self-improving research agent with constraint-wise verification
AutoformBot
Multi-agent system for scaling mathematical formalization in Lean 4 with collaborative verification
Compass Marine Data
Expert-guided LLM agent for extracting structured marine science data from research papers
DataFactory
Multi-agent framework for advanced table question answering with collaborative reasoning
DocSage
Multi-document QA agent with entity relationship tracking beyond standard RAG
EvoKernel
Self-evolving framework for NPU kernel synthesis without fine-tuning or large datasets
KARL
RL-trained enterprise search agents with multi-regime evaluation benchmark
KernelSkill
Multi-agent framework that systematically optimizes GPU kernels using expert rules over LLM heuristics
PosterMELD
Multi-agent system that transforms scientific papers into print-ready posters automatically
Tycho
Game-playing agent that builds programmatic world models for active abstraction and skill learning
UIS-Digger
Research agent that discovers unindexed web content beyond traditional search engines
dev tools
(15)Agent Memory Distillation
Training-free knowledge transfer from large to small agents via hierarchical memory
AgentCheck
Debug LLM agents with reproducible recordings and controlled interventions over MCP
Cognitive Firewall
Hybrid edge-cloud security defense against prompt injection attacks on browser AI agents
flexvec
SQL-based vector retrieval with runtime embedding manipulation for AI agents
HARP
Research platform for systematic HCI studies of human-AI interaction with live LLM agents
HyperTool
Multi-step tool execution framework that hides intermediate dataflow from reasoning traces
LEDGER
Claim-to-evidence trace graphs for auditing and verifying LLM agent reasoning
MathCoPilot
Human-in-the-loop AI system for interactive mathematical theorem proving and formalization
PhysAssistBench
Benchmark for evaluating LLM agents in doctor-patient-EHR clinical assistance workflows
PIPES
Secure agent perception through data provenance tracking and authority controls
PostTrainBench
Benchmark for evaluating autonomous post-training of LLMs under compute constraints
StagedWorkspace
Versioned workspace infrastructure ensuring explicit state contracts for knowledge-work agents
SWE-Pruner Pro
Context pruning for coding agents using internal representations to remove irrelevant code
TA-Mem
Tool-augmented memory system enabling dynamic retrieval for long-term conversational AI
VRR-Stop
Principled stopping framework for LLM agent repair loops that prevents over-correction
frameworks
(14)DSPy
Framework for programming — not prompting — LLMs — 33K+ stars
smolagents
Lightweight agent framework by HuggingFace — minimal code, maximum control
CAMEL-AI
Multi-agent role-playing framework for communicative AI research — 18K stars
AdMem
Multi-level memory framework enabling agents to learn from past tasks, failures, and procedures
Ares
Adaptive reasoning framework that optimizes LLM inference costs by dynamically scaling effort
BrainAgent
Multi-agent framework for autonomous brain signal analysis and BCI development
CAST (CausalSteward)
Human-in-the-loop framework for causal discovery using LLM agents and divide-conquer strategies
EchoGuard
Knowledge Graph-powered memory framework for detecting manipulation in long-term AI conversations
LLM-Wiki
Agent-native retrieval system using Retrieval-as-Reasoning for dynamic knowledge navigation
ReASearch
Framework for autonomous reasoning-driven optimization across prompts, programs, and ML workflows
RoboClaw
VLM-driven robotics framework for autonomous long-horizon task execution and policy learning
SPD-RAG
Hierarchical multi-agent RAG system that assigns specialized sub-agents per document
TopoAgent
Graph-based agent framework that evolves topological states for complex multimodal reasoning
XSkill
Continual learning framework enabling multimodal agents to improve from experience without retraining