toolAngestromTrust 64Published 3mo agoLive · 3mo ago
AgentTrace
A debugger that visualizes an agent's step-by-step reasoning.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownAgentCore-8B →
- LinkedLinked via unknownA field guide to AI agents in 2026 →
- LinkedLinked via unknownnicolbl95/MultiAgent-Financial-Analyzer →
- LinkedLinked via unknownOpenRCA 2.0: From Outcome Labels to Causal Process Supervision →
- LinkedLinked via unknownAgentic Resource Discovery: Let agents search →
- LinkedLinked via unknownagent-tools →
- LinkedLinked via unknownSelf-rewarding agents that retrace failures →
Related to
Related to (incoming)
reponicolbl95/MultiAgent-Financial-AnalyzerpaperOpenRCA 2.0: From Outcome Labels to Causal Process Supervisionrepoagent-toolspaperSelf-rewarding agents that retrace failurestutorialMake an agent that uses toolsrepoCrazyDashTool/Local-Agent-StudiopaperAgentic Hardware Design as Repository-Level Code EvolutionpaperA Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure DiagnosispaperRehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question AnsweringpaperMulti-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation ThreatspaperSWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding SessionspaperTraceLab: Characterizing Coding Agent Workloads for LLM ServingpaperBayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question AnsweringpaperSWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction TestspaperKnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformersrepogptme/gptmerepopromptfoo/promptfoorepoTracecatHQ/tracecatrepoyvgude/lean-ctxrepoBigBoySlave/Agents-Promptsrepocomet-ml/opikrepogolobokov.misha/llm-review-agentsreposquirrelscan/squirrelscanrepoagentscope-ai/agentscopereposammcj/agentic-codingrepotrpc-group/trpc-agent-gorepoIkalus1988/MisakaNetrepolitefuse/litefusepaperSkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill MarketplacespaperReasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational studyrepoeunomia-bpf/agentsightrepoanatomia-dev/anatomiarepoagentcommunity/agent-identity-discoveryrepovincentkoc/dotskillsrepoLuD1161/agentjailrepoinference-gateway/adkrepoastronomer/agentsrepoAgent-Field/sec-afreposmithersai/smithersrepopatoles/agent-flowrepoexplainX/explainxreponomograph/jigpaperTracing Agentic Failure from the Flow of Successrepomicrosoft/DebugMCPrepoevilmartians/agent-prismrepomicrosoft/debug-gymrepofirst-fluke/oh-my-agent
Covers (incoming)
newsAnthropic launches Cowork, a Claude Desktop agent that works in your files — no coding requirednewsAgentic Resource Discovery: Let agents searchnewsOpen-source agent framework crosses 50k starsnewsDebugging production agents with Amazon Bedrock AgentCore ObservabilitynewsAI agents are not your “coworkers”newsShow HN: AnalystAIPack – 118 runnable agent skills for malware analysis and REnewsAgent frameworks solved one problem. What solves the next one?newsDecypher: A Deep Semantic Code Graph for Agentic Coding and Engineering (Now in Beta)newsI don't trust AGENTS.md as a secret-redaction boundary
Related across the graph
newsDecypher: A Deep Semantic Code Graph for Agentic Coding and Engineering (Now in Beta)repoIkalus1988/MisakaNetpaperTraceLab: Characterizing Coding Agent Workloads for LLM Servingrepoagentcommunity/agent-identity-discoveryrepotrpc-group/trpc-agent-gorepoastronomer/agentsrepoevilmartians/agent-prismpaperTracing Agentic Failure from the Flow of SuccesspaperMulti-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threatsrepomicrosoft/debug-gymtutorialMake an agent that uses toolsnewsAgent frameworks solved one problem. What solves the next one?repoexplainX/explainxpaperSelf-rewarding agents that retrace failuresnewsI don't trust AGENTS.md as a secret-redaction boundarynewsAnthropic launches Cowork, a Claude Desktop agent that works in your files — no coding requirednewsOpen-source agent framework crosses 50k starsrepoBigBoySlave/Agents-Promptsreposquirrelscan/squirrelscanpaperOpenRCA 2.0: From Outcome Labels to Causal Process SupervisionrepoTracecatHQ/tracecatrepoagentscope-ai/agentscopepaperBayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answeringrepolitefuse/litefusenewsDebugging production agents with Amazon Bedrock AgentCore ObservabilityrepoLuD1161/agentjailreposmithersai/smithersrepoAgent-Field/sec-afrepoeunomia-bpf/agentsightnewsAgentic Resource Discovery: Let agents searchpaperSkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill MarketplacespaperRehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answeringrepopatoles/agent-flowrepocomet-ml/opikreposammcj/agentic-codingreponicolbl95/MultiAgent-Financial-Analyzerreponomograph/jignewsShow HN: AnalystAIPack – 118 runnable agent skills for malware analysis and RErepoyvgude/lean-ctxpaperA Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure Diagnosisrepoanatomia-dev/anatomiarepoCrazyDashTool/Local-Agent-StudionewsAI agents are not your “coworkers”articleA field guide to AI agents in 2026paperReasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational studymodelAgentCore-8BpaperKnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformersrepovincentkoc/dotskillspaperSWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Testsrepofirst-fluke/oh-my-agentrepogptme/gptmerepopromptfoo/promptfoopaperSWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessionsrepomicrosoft/DebugMCPrepogolobokov.misha/llm-review-agentsrepoinference-gateway/adkrepoagent-toolspaperAgentic Hardware Design as Repository-Level Code Evolution