• Home
  • knowledge_base
  • memory
  • plans
  • src
Pages
  • memory
    • 2026-07
      • 12
        • composable-context
          • context-composition-references
          • deep-research-report
          • review-cc
          • review-cd
          • white-draft-cc
          • white-draft-cd
      • 13
        • harborworks-composition-experiment
          • fixtures
            • repos
              • harborworks-analysis-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • analyze-signal
                    • SKILL
                  • check-evidence
                    • SKILL
                  • compare-baseline
                    • SKILL
                  • flag-anomaly
                    • SKILL
                  • identify-driver
                    • SKILL
                  • segment-findings
                    • SKILL
              • harborworks-briefing-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • cite-findings
                    • SKILL
                  • draft-brief
                    • SKILL
                  • format-decision
                    • SKILL
                  • list-risks
                    • SKILL
                  • prepare-handoff
                    • SKILL
                  • summarize-status
                    • SKILL
              • harborworks-context-core
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-provenance
                    • SKILL
                  • compare-revisions
                    • SKILL
                  • explain-policy
                    • SKILL
                  • inspect-context
                    • SKILL
                  • list-exports
                    • SKILL
                  • trace-artifact
                    • SKILL
              • harborworks-customer-operations
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-sla
                    • SKILL
                  • explain-escalation
                    • SKILL
                  • inspect-case
                    • SKILL
                  • review-feedback
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-account
                    • SKILL
              • harborworks-data-governance
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-retention
                    • SKILL
                  • explain-lineage
                    • SKILL
                  • inspect-dataset
                    • SKILL
                  • review-quality
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-owner
                    • SKILL
              • harborworks-facilities-operations
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-inspection
                    • SKILL
                  • explain-maintenance
                    • SKILL
                  • inspect-work-order
                    • SKILL
                  • review-safety
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-asset
                    • SKILL
              • harborworks-operations-workbench
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • compare-surface
                    • SKILL
                  • explain-exclusion
                    • SKILL
                  • inspect-collision
                    • SKILL
                  • list-composed-context
                    • SKILL
                  • select-scope
                    • SKILL
                  • trace-selected-artifact
                    • SKILL
              • harborworks-remediation-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • assess-impact
                    • SKILL
                  • create-checklist
                    • SKILL
                  • plan-followup
                    • SKILL
                  • prioritize-fix
                    • SKILL
                  • propose-action
                    • SKILL
                  • verify-resolution
                    • SKILL
              • harborworks-software-delivery
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-pipeline
                    • SKILL
                  • explain-deployment
                    • SKILL
                  • inspect-release
                    • SKILL
                  • review-change
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-service
                    • SKILL
            • variants
              • harborworks-context-core-r2
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-provenance
                    • SKILL
                  • compare-revisions
                    • SKILL
                  • explain-policy
                    • SKILL
                  • inspect-context
                    • SKILL
                  • list-exports
                    • SKILL
                  • trace-artifact
                    • SKILL
          • candidate-rules
          • run-001
          • run-002
      • 19
        • okf-wrapper
Pages
  • memory
    • 2026-07
      • 12
        • composable-context
          • context-composition-references
          • deep-research-report
          • review-cc
          • review-cd
          • white-draft-cc
          • white-draft-cd
      • 13
        • harborworks-composition-experiment
          • fixtures
            • repos
              • harborworks-analysis-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • analyze-signal
                    • SKILL
                  • check-evidence
                    • SKILL
                  • compare-baseline
                    • SKILL
                  • flag-anomaly
                    • SKILL
                  • identify-driver
                    • SKILL
                  • segment-findings
                    • SKILL
              • harborworks-briefing-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • cite-findings
                    • SKILL
                  • draft-brief
                    • SKILL
                  • format-decision
                    • SKILL
                  • list-risks
                    • SKILL
                  • prepare-handoff
                    • SKILL
                  • summarize-status
                    • SKILL
              • harborworks-context-core
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-provenance
                    • SKILL
                  • compare-revisions
                    • SKILL
                  • explain-policy
                    • SKILL
                  • inspect-context
                    • SKILL
                  • list-exports
                    • SKILL
                  • trace-artifact
                    • SKILL
              • harborworks-customer-operations
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-sla
                    • SKILL
                  • explain-escalation
                    • SKILL
                  • inspect-case
                    • SKILL
                  • review-feedback
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-account
                    • SKILL
              • harborworks-data-governance
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-retention
                    • SKILL
                  • explain-lineage
                    • SKILL
                  • inspect-dataset
                    • SKILL
                  • review-quality
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-owner
                    • SKILL
              • harborworks-facilities-operations
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-inspection
                    • SKILL
                  • explain-maintenance
                    • SKILL
                  • inspect-work-order
                    • SKILL
                  • review-safety
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-asset
                    • SKILL
              • harborworks-operations-workbench
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • compare-surface
                    • SKILL
                  • explain-exclusion
                    • SKILL
                  • inspect-collision
                    • SKILL
                  • list-composed-context
                    • SKILL
                  • select-scope
                    • SKILL
                  • trace-selected-artifact
                    • SKILL
              • harborworks-remediation-methods
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • assess-impact
                    • SKILL
                  • create-checklist
                    • SKILL
                  • plan-followup
                    • SKILL
                  • prioritize-fix
                    • SKILL
                  • propose-action
                    • SKILL
                  • verify-resolution
                    • SKILL
              • harborworks-software-delivery
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-pipeline
                    • SKILL
                  • explain-deployment
                    • SKILL
                  • inspect-release
                    • SKILL
                  • review-change
                    • SKILL
                  • summarize-status
                    • SKILL
                  • trace-service
                    • SKILL
            • variants
              • harborworks-context-core-r2
                • knowledge_base
                  • glossary
                  • overview
                • skills
                  • check-provenance
                    • SKILL
                  • compare-revisions
                    • SKILL
                  • explain-policy
                    • SKILL
                  • inspect-context
                    • SKILL
                  • list-exports
                    • SKILL
                  • trace-artifact
                    • SKILL
          • candidate-rules
          • run-001
          • run-002
      • 19
        • okf-wrapper

References from the Context Composition Deep Research Report

Deduplicated reference list extracted from the citations used in the report. Total: 78 references.

1Vendor docsAnthropicHow Claude remembers your project - Claude Code Docshttps://docs.anthropic.com/en/docs/claude-code/memory
2Vendor docsAnthropicCreate custom subagents - Claude Code Docshttps://docs.anthropic.com/en/docs/claude-code/sub-agents
3Vendor docsAnthropicAgent SDK overview - Claude Code Docshttps://docs.anthropic.com/en/docs/claude-code/sdk
4Vendor engineeringAnthropicEffective context engineering for AI agentshttps://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
5Vendor docsOpenAIAgents SDK - OpenAI APIhttps://developers.openai.com/api/docs/guides/agents
6Vendor docsOpenAIConversation state - OpenAI APIhttps://developers.openai.com/api/docs/guides/conversation-state
7Vendor docsOpenAIPrompt caching - OpenAI APIhttps://developers.openai.com/api/docs/guides/prompt-caching
8Vendor docsOpenAIUsing tools - OpenAI APIhttps://developers.openai.com/api/docs/guides/tools
9Vendor docsOpenAIMCP and Connectors - OpenAI APIhttps://developers.openai.com/api/docs/guides/tools-connectors-mcp
10Vendor docsOpenAISkills - OpenAI APIhttps://developers.openai.com/api/docs/guides/tools-skills
11Vendor docsOpenAICompaction - OpenAI APIhttps://developers.openai.com/api/docs/guides/compaction
12Vendor engineeringOpenAIUsing skills to accelerate OSS maintenancehttps://developers.openai.com/blog/skills-agents-sdk
13Vendor engineeringOpenAIShell + Skills + Compaction: Tips for long-running agentshttps://developers.openai.com/blog/skills-shell-tips
14Vendor docsGoogleAgent Development Kit - Gemini Enterprise Agent Platformhttps://docs.cloud.google.com/gemini-enterprise-agent-platform/build/adk
15Vendor docsGoogleGemini Enterprise Agent Platformhttps://docs.cloud.google.com/gemini-enterprise-agent-platform
16Vendor docsGoogleState - Agent Development Kit (ADK)https://adk.dev/sessions/state/
17Vendor docsGoogleSet up Memory Bank - Gemini Enterprise Agent Platformhttps://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank/setup
18Vendor docsGoogleAgent Registry - Gemini Enterprise Agent Platformhttps://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-registry
19Vendor docsGoogleUse the Agent Platform remote MCP serverhttps://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/use-agent-platform-mcp
20Vendor docsMetaGet started with Meta Model APIhttps://ai.developer.meta.com/docs/getting-started/overview
21Vendor docsMetaTool calling with Llama APIhttps://llama.developer.meta.com/docs/guides/tool-guide/
22Vendor docsMetaOpenAI compatibility - Llama APIhttps://llama.developer.meta.com/docs/features/compatibility/
23Vendor docsMetaJSON Structured Output - Llama APIhttps://llama.developer.meta.com/docs/features/structured-output/
24Vendor docsMicrosoftMicrosoft Agent Framework Overviewhttps://learn.microsoft.com/en-us/agent-framework/overview/
25Vendor docsMicrosoftStep 4: Memory & Persistencehttps://learn.microsoft.com/en-us/agent-framework/get-started/memory
26Vendor docsMicrosoftOrchestrate agent behavior with generative AI - Copilot Studiohttps://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-generative-actions
27Vendor docsMicrosoftMulti-agent orchestration patterns and best practices - Copilot Studiohttps://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/multi-agent-patterns
28Framework docsPydanticPydantic AI overviewhttps://pydantic.dev/docs/ai/overview/
29Framework docsPydanticCapabilities - Pydantic AIhttps://pydantic.dev/docs/ai/core-concepts/capabilities/
30Framework docsPydanticDurable execution overview - Pydantic AIhttps://pydantic.dev/docs/ai/integrations/durable_execution/overview/
31Framework docsPydanticMCP overview - Pydantic AIhttps://pydantic.dev/docs/ai/mcp/overview/
32Framework docsPydanticMulti-Agent Patterns - Pydantic AIhttps://pydantic.dev/docs/ai/guides/multi-agent-applications/
33Framework docsOpenCodeRules - OpenCodehttps://opencode.ai/docs/rules/
34Framework docsOpenCodeCommands - OpenCodehttps://opencode.ai/docs/commands/
35Framework docsOpenCodeConfig - OpenCodehttps://opencode.ai/docs/config/
36Framework docsOpenCodeCustom Tools - OpenCodehttps://opencode.ai/docs/custom-tools/
37Framework docsOpenCodeProviders - OpenCodehttps://opencode.ai/docs/providers/
38Framework docsOpenCodeReferences - OpenCodehttps://opencode.ai/docs/references/
39Framework docsLangChain / LangGraphLangGraph overviewhttps://docs.langchain.com/oss/python/langgraph/overview
40Framework docsLangChain / LangGraphPersistence - LangGraphhttps://docs.langchain.com/oss/python/langgraph/persistence
41Framework docsLangChain / LangGraphLong-term memory - LangChainhttps://docs.langchain.com/oss/python/langchain/long-term-memory
42Framework docsLangChain / LangGraphMemory overview - LangChainhttps://docs.langchain.com/oss/python/concepts/memory
43Framework docsLangChain / LangGraphMemory - Deep Agentshttps://docs.langchain.com/oss/python/deepagents/memory
44Framework docsLlamaIndexMemory - LlamaIndexhttps://developers.llamaindex.ai/python/framework/module_guides/deploying/agents/memory/
45Framework docsLlamaIndexAgent Workflows - LlamaIndexhttps://developers.llamaindex.ai/typescript/framework/modules/agents/agent_workflow/
46Framework docsCrewAICrewAI Documentationhttps://docs.crewai.com/
47RepositoryCrewAIcrewAIInc/crewAIhttps://github.com/crewaiinc/crewai
48Framework docsHugging Facesmolagentshttps://huggingface.co/docs/smolagents/en/index
49Framework docsHugging FaceAgents - smolagentshttps://huggingface.co/docs/smolagents/en/reference/agents
50Protocol / standardModel Context ProtocolMCP Specification 2025-06-18https://modelcontextprotocol.io/specification/2025-06-18
51Protocol / standardModel Context ProtocolMCP Resources specificationhttps://modelcontextprotocol.io/specification/2025-06-18/server/resources
52Protocol / standardA2AA2A Protocolhttps://a2a-protocol.org/latest/
53Protocol / standardA2AWhat is A2A?https://a2a-protocol.org/latest/topics/what-is-a2a/
54Protocol / standardA2AAgent Discoveryhttps://a2a-protocol.org/latest/topics/agent-discovery/
55Research paperYao et al.ReAct: Synergizing Reasoning and Acting in Language Modelshttps://arxiv.org/abs/2210.03629
56Research paperSchick et al.Language Models Can Teach Themselves to Use Tools (Toolformer)https://arxiv.org/abs/2302.04761
57Research paperPark et al.Generative Agents: Interactive Simulacra of Human Behaviorhttps://arxiv.org/abs/2304.03442
58Research paperShinn et al.Reflexion: Language Agents with Verbal Reinforcement Learninghttps://openreview.net/forum?id=vAElhFcKW6
59Research paperWang et al.Voyager: An Open-Ended Embodied Agent with Large Language Modelshttps://arxiv.org/abs/2305.16291
60Research paperPacker et al.MemGPT: Towards LLMs as Operating Systemshttps://arxiv.org/abs/2310.08560
61Research paperSarthi et al.RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalhttps://arxiv.org/abs/2401.18059
62Research paperEdge et al.A Graph RAG Approach to Query-Focused Summarizationhttps://arxiv.org/abs/2404.16130
63Research paperGutiérrez et al.HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelshttps://arxiv.org/html/2405.14831v2
64Research paperGutiérrez et al.From RAG to Memory: Non-Parametric Continual Learning for Large Language Models (HippoRAG 2)https://arxiv.org/abs/2502.14802
65SurveyHuang et al.Understanding the planning of LLM agents: A surveyhttps://arxiv.org/abs/2402.02716
66Research paper / benchmarkMaharana et al.Evaluating Very Long-Term Conversational Memory of LLM Agents (LoCoMo)https://arxiv.org/abs/2402.17753
67Research paper / benchmarkWu et al.LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memoryhttps://arxiv.org/abs/2410.10813
68SurveyLuo et al.Large Language Model Agent: A Survey on Methodology, Applications and Challengeshttps://arxiv.org/abs/2503.21460
69SurveyHu et al.Memory in the Age of AI Agentshttps://arxiv.org/abs/2512.13564
70SurveyLuo et al.A Survey on the Evolution of LLM Agent Memory: Mechanism, Optimization, and Evaluationhttps://arxiv.org/abs/2605.06716
71Research paperAuthors as listed on arXivMemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelshttps://arxiv.org/html/2505.22101v1
72Research paperAuthors as listed on arXivExperience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentshttps://arxiv.org/html/2604.15877
73Research paperAuthors as listed on arXivInfini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memoryhttps://arxiv.org/html/2606.10677v1
74Research paper / benchmarkWu et al.LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagueshttps://arxiv.org/abs/2605.12493
75Security researchAuthors as listed on arXivA Systematic Study of Memory Poisoning Attacks in LLM Agentshttps://arxiv.org/html/2606.04329v1
76Security researchAuthors as listed on arXivMemMorph: Tool Hijacking in LLM Agents via Memory Poisoninghttps://arxiv.org/html/2605.26154v1
77Security researchAuthors as listed on arXivMemory Control Flow Attacks on LLM Agentshttps://arxiv.org/html/2603.15125v3
78Survey / securityAuthors as listed on arXivA Survey on the Security of Long-Term Memory in LLM Agentshttps://arxiv.org/html/2604.16548v1
On this page
  • References from the Context Composition Deep Research Report