MCPcopy Create free account

hub / github.com/vectorize-io/hindsight / types & classes

Types & classes2,579 in github.com/vectorize-io/hindsight

↓ 156 callersClassRequestContext
Context for request authentication and authorization. This dataclass carries authentication data from HTTP requests to the memory engine
hindsight-api-slim/hindsight_api/models.py:15
↓ 104 callersClassHindsightTools
Agno Toolkit providing Hindsight memory tools. Registers retain, recall, and reflect as agent-callable tools following the same pattern as Ag
hindsight-integrations/agno/hindsight_agno/tools.py:67
↓ 92 callersClassMockResult
Mock result object for testing filter_results_by_tags.
hindsight-api-slim/tests/test_tags_visibility.py:200
↓ 70 callersClassHindsight
High-level, easy-to-use Hindsight API client. This class provides simplified methods for the most common operations: retain, recall, ref
hindsight-clients/python/hindsight_client/hindsight_client.py:63
↓ 59 callersClassSafeHindsight
Hindsight client wrapper that applies Superagent safety checks to memory operations. Wraps retain, recall, and reflect with configurable Guard (p
hindsight-integrations/superagent/hindsight_superagent/middleware.py:59
↓ 58 callersClassMapField
A field within a map-type entity label group. Supports recursion via type='map'.
hindsight-api-slim/hindsight_api/engine/retain/entity_labels.py:21
↓ 51 callersClassLLMToolCallResult
Result from an LLM call that may include tool calls.
hindsight-api-slim/hindsight_api/engine/response_models.py:28
↓ 51 callersClassWorkerPoller
Polls the database for pending tasks and executes them. Uses FOR UPDATE SKIP LOCKED for safe distributed claiming, allowing multiple wor
hindsight-api-slim/hindsight_api/worker/poller.py:129
↓ 48 callersClassLLMProvider
Unified LLM provider. Supports OpenAI, Groq, Ollama (OpenAI-compatible), and Gemini.
hindsight-api-slim/hindsight_api/engine/llm_wrapper.py:504
↓ 48 callersClassTokenUsage
Token usage metrics for LLM calls. Tracks input/output tokens for a single request to enable per-request cost tracking and monitoring.
hindsight-api-slim/hindsight_api/engine/response_models.py:87
↓ 45 callersClassIntegrationMeta
hindsight-dev/hindsight_dev/generate_changelog.py:33
↓ 44 callersClassA
hindsight-api-slim/tests/test_gemini_cache.py:79
↓ 44 callersClassLLMToolCall
A tool call requested by the LLM.
hindsight-api-slim/hindsight_api/engine/response_models.py:16
↓ 43 callersClassMemoryEngine
Advanced memory system using temporal and semantic linking with PostgreSQL. This class provides: - Embedding generation for semantic sea
hindsight-api-slim/hindsight_api/engine/memory_engine.py:877
↓ 41 callersClassHindsightToolSpec
LlamaIndex tool spec providing Hindsight memory tools. Exposes retain, recall, and reflect as tools that LlamaIndex agents can call natively
hindsight-integrations/llamaindex/hindsight_llamaindex/tools.py:20
↓ 38 callersClassDaemonEmbedManager
Production embed manager using daemon-based architecture with profile isolation.
hindsight-embed/hindsight_embed/daemon_embed_manager.py:106
↓ 36 callersInterfaceChatMessage
hindsight-integrations/chat/src/types.ts:130
↓ 36 callersClassLabelValue
A single allowed value for a label group.
hindsight-api-slim/hindsight_api/engine/retain/entity_labels.py:14
↓ 31 callersClassLabelGroup
A label group (dimension) with its type and allowed values.
hindsight-api-slim/hindsight_api/engine/retain/entity_labels.py:33
↓ 30 callersClassBankWriteContext
Context for a bank write operation validation (pre-operation).
hindsight-api-slim/hindsight_api/extensions/operation_validator.py:392
↓ 30 callersClassEntityLabelsConfig
Entity labels configuration for a bank (controlled vocabulary).
hindsight-api-slim/hindsight_api/engine/retain/entity_labels.py:45
↓ 29 callersClassBankReadContext
Context for a bank read operation validation (pre-operation).
hindsight-api-slim/hindsight_api/extensions/operation_validator.py:383
↓ 27 callersClassFakeComposio
Stand-in for a Composio instance for fast, offline unit tests.
hindsight-integrations/composio/tests/test_tools.py:40
↓ 27 callersClassFakeMember
Stands in for an LLMProvider member. ``behavior`` is a value to return, or an exception instance/class to raise. Each ``call`` / ``call_with_
hindsight-api-slim/tests/test_multi_llm_provider.py:20
↓ 27 callersClassGeminiEmbeddings
Google embeddings via the google.genai SDK. Supports both: 1. Gemini API (api.generativeai.google.com) with API key authentication 2
hindsight-api-slim/hindsight_api/engine/embeddings.py:1361
↓ 26 callersClassFakeHTTPResponse
Minimal urllib response mock.
hindsight-integrations/cursor-cli/tests/conftest.py:89
↓ 26 callersClassHindsightClient
HTTP client for the Hindsight API.
hindsight-integrations/claude-code/scripts/lib/client.py:44
↓ 25 callersClassFakeCtx
Stand-in for the Composio SessionContext injected into tools.
hindsight-integrations/composio/tests/test_tools.py:47
↓ 25 callersClassProfileManager
Manages configuration profiles for hindsight-embed.
hindsight-embed/hindsight_embed/profile_manager.py:147
↓ 24 callersClassFakeHTTPResponse
Minimal urllib response mock.
hindsight-integrations/claude-code/tests/conftest.py:80
↓ 24 callersClassHindsightCallback
LiteLLM custom logger that integrates with Hindsight memory system. This callback handler: 1. Injects relevant memories into prompts before L
hindsight-integrations/litellm/hindsight_litellm/callbacks.py:83
↓ 23 callersClassConfigResolver
Resolves hierarchical configuration with tenant/bank overrides.
hindsight-api-slim/hindsight_api/config_resolver.py:64
↓ 23 callersClassHindsightError
Exception raised when a Hindsight operation fails. This is raised when inject_memories=True and recall fails, or when store_conversations=Tru
hindsight-integrations/litellm/hindsight_litellm/callbacks.py:69
↓ 23 callersClassOracleBackend
DatabaseBackend implementation wrapping an oracledb async connection pool.
hindsight-api-slim/hindsight_api/engine/db/oracle.py:1196
↓ 23 callersClassSyncTaskBackend
Synchronous task backend that executes tasks immediately. This is useful for tests and embedded/CLI usage where we don't want background
hindsight-api-slim/hindsight_api/engine/task_backend.py:95
↓ 22 callersClassAuthenticationError
Raised when authentication fails.
hindsight-api-slim/hindsight_api/extensions/tenant.py:11
↓ 20 callersClassTenant
Represents a tenant for worker discovery. Used by list_tenants() to return tenant information including the PostgreSQL schema name for d
hindsight-api-slim/hindsight_api/extensions/tenant.py:34
↓ 19 callersClassLiteLLMSDKEmbeddings
LiteLLM SDK embeddings for direct API integration. Supports embeddings via LiteLLM SDK without requiring a proxy server. Supported provi
hindsight-api-slim/hindsight_api/engine/embeddings.py:1182
↓ 19 callersClassRemoteTEICrossEncoder
Remote cross-encoder implementation using HuggingFace Text Embeddings Inference (TEI) HTTP API. TEI supports reranking via the /rerank endpo
hindsight-api-slim/hindsight_api/engine/cross_encoder.py:344
↓ 19 callersClassResultRow
Dict-like row interface returned by all database operations.
hindsight-api-slim/hindsight_api/engine/db/result.py:16
↓ 19 callersClassRetainContent
Input content item to be retained as memories. Represents a single piece of content to extract facts from.
hindsight-api-slim/hindsight_api/engine/retain/types.py:49
↓ 18 callersClassChunkMetadata
Metadata about a text chunk. Used to track which facts were extracted from which chunks.
hindsight-api-slim/hindsight_api/engine/retain/types.py:68
↓ 18 callersClassEntity
An entity extracted from text.
hindsight-api-slim/hindsight_api/engine/retain/fact_extraction.py:117
↓ 18 callersClassFakeResp
hindsight-integrations/claude-code/tests/test_client.py:31
↓ 17 callersClassFakeHTTPResponse
Minimal urllib response mock.
hindsight-integrations/codex/tests/conftest.py:76
↓ 17 callersClassOpenAICompatibleLLM
LLM provider for OpenAI-compatible APIs. Supports: - OpenAI: Standard models (GPT-4, GPT-4o) and reasoning models (o1, o3, GPT-5) -
hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py:414
↓ 17 callersClassTagGroupLeaf
A leaf tag filter: matches memories by tag list and match mode.
hindsight-api-slim/hindsight_api/engine/search/tags.py:229
↓ 17 callersClass_ConsolidationBatchResponse
hindsight-api-slim/hindsight_api/engine/consolidation/consolidator.py:494
↓ 16 callersClassBankStatsCache
Per-process TTL cache keyed on (schema, bank_id). `ttl_seconds <= 0` disables caching: each call passes straight through to the loader. `max_
hindsight-api-slim/hindsight_api/engine/bank_stats_cache.py:30
↓ 16 callersClassHindsightMemoryService
Pipecat frame processor that adds Hindsight persistent memory. Place this between the user context aggregator and the LLM service:: pipe
hindsight-integrations/pipecat/hindsight_pipecat/memory.py:68
↓ 16 callersClassHindsightMemoryWrapper
Haystack ``Toolset`` with optional auto-recall and auto-retain. Groups Hindsight memory tools into a single toolset and optionally adds autom
hindsight-integrations/haystack/hindsight_haystack/tools.py:623
↓ 16 callersClassMemoryFact
A single memory fact returned by search or think operations. This represents a unit of information stored in the memory system, includin
hindsight-api-slim/hindsight_api/engine/response_models.py:216
↓ 15 callersClassHindsightRetainTool
Store information to long-term memory for later retrieval. Use this to save important facts, user preferences, decisions, or any information
hindsight-integrations/smolagents/hindsight_smolagents/tools.py:45
↓ 15 callersClassLiteLLMSDKCrossEncoder
LiteLLM SDK cross-encoder for direct API integration. Supports reranking via LiteLLM SDK without requiring a proxy server. Supported pro
hindsight-api-slim/hindsight_api/engine/cross_encoder.py:1174
↓ 15 callersClassMentalModelTrigger
Trigger settings for a mental model.
hindsight-api-slim/hindsight_api/api/http.py:1965
↓ 15 callersClassParagraphBlock
hindsight-api-slim/hindsight_api/engine/reflect/structured_doc.py:44
↓ 14 callersClassGoogleCrossEncoder
Google Discovery Engine cross-encoder using the Ranking REST API. Uses httpx + google-auth for lightweight REST calls (no gRPC/protobuf).
hindsight-api-slim/hindsight_api/engine/cross_encoder.py:1417
↓ 14 callersClassHindsightVapiWebhook
Webhook handler that adds Hindsight persistent memory to Vapi voice calls. Handles two Vapi server events: - ``assistant-request``: Recalls
hindsight-integrations/vapi/hindsight_vapi/webhook.py:71
↓ 14 callersClassMCPToolsConfig
Configuration for MCP tools registration.
hindsight-api-slim/hindsight_api/mcp_tools.py:75
↓ 14 callersClassRetainInput
hindsight-integrations/composio/hindsight_composio/tools.py:42
↓ 13 callersClassApiClient
Generic API client for OpenAPI client library builds. OpenAPI generic API client. This client handles the client- server communication, and i
hindsight-clients/python/hindsight_client_api/api_client.py:45
↓ 13 callersClassCohereCrossEncoder
Cohere cross-encoder implementation using the Cohere Rerank API. Supports rerank-english-v3.0 and rerank-multilingual-v3.0 models.
hindsight-api-slim/hindsight_api/engine/cross_encoder.py:639
↓ 13 callersClassMemoryHookConfig
Configuration for automatic memory hooks. Attributes: auto_recall: Inject relevant memories into the system prompt on each ``
hindsight-integrations/claude-agent-sdk/hindsight_claude_agent_sdk/hooks.py:83
↓ 13 callersClass_Args
Minimal namespace for testing CLI commands.
hindsight-integrations/cursor/tests/test_cli.py:34
↓ 12 callersClassClaimedTask
A task claimed from the database with its schema context.
hindsight-api-slim/hindsight_api/worker/poller.py:106
↓ 12 callersClassConfiguration
This class contains various settings of the API client. :param host: Base url. :param ignore_operation_servers Boolean to ignore operat
hindsight-clients/python/hindsight_client_api/configuration.py:132
↓ 12 callersClassExtractedFact
Fact extracted from content by the LLM. This is the raw output from fact extraction before processing.
hindsight-api-slim/hindsight_api/engine/retain/types.py:107
↓ 12 callersClassFakeHTTPResponse
Minimal urllib response mock.
hindsight-integrations/omo/tests/conftest.py:70
↓ 12 callersClassHindsightEmbedded
Hindsight client with automatic daemon lifecycle management. This client uses the same daemon management interface as hindsight-embed CLI,
hindsight-all/hindsight/embedded.py:48
↓ 12 callersClassHindsightRecallTool
Search long-term memory for relevant information. Use this to find previously stored facts, preferences, or context. Returns a numbered list
hindsight-integrations/smolagents/hindsight_smolagents/tools.py:113
↓ 12 callersClassProviderInfo
A provider the wizard can configure.
hindsight-embed/hindsight_embed/control_center/providers.py:11
↓ 11 callersClassHindsightCallSettings
Unified settings for Hindsight memory operations. All fields here can be: - Set as defaults via configure() or set_defaults() - Overridde
hindsight-integrations/litellm/hindsight_litellm/config.py:52
↓ 11 callersClassRecallInput
hindsight-integrations/composio/hindsight_composio/tools.py:46
↓ 11 callersClassTenantContext
Tenant context returned by authentication. Contains the PostgreSQL schema name for tenant isolation. All database queries will use fully
hindsight-api-slim/hindsight_api/extensions/tenant.py:21
↓ 10 callersClassEmbeddedPostgres
Manages an embedded PostgreSQL server instance using pg0-embedded.
hindsight-api-slim/hindsight_api/pg0.py:17
↓ 10 callersClassFakeBankConfigBackend
Minimal backend for ConfigResolver bank-config tests.
hindsight-api-slim/tests/test_hierarchical_config.py:44
↓ 10 callersClassGeminiCacheManager
Per-process map of (prefix fingerprint) → CachedContent name. Thread-safe across asyncio tasks via a single ``asyncio.Lock``. The create/refr
hindsight-api-slim/hindsight_api/engine/providers/gemini_cache.py:67
↓ 10 callersClassHindsightReflectTool
Synthesize a thoughtful answer from long-term memories. Use this when you need a coherent summary or reasoned response about what you know, r
hindsight-integrations/smolagents/hindsight_smolagents/tools.py:182
↓ 10 callersClassLLMSpanRecorder
Records OpenTelemetry spans for LLM calls following GenAI semantic conventions.
hindsight-api-slim/hindsight_api/tracing.py:255
↓ 10 callersClassLlamaParseParser
LlamaParse file parser using LlamaIndex's hosted parsing service. Uploads files to the LlamaParse API, polls until the parse job completes,
hindsight-api-slim/hindsight_api/engine/parsers/llama_parse.py:23
↓ 10 callersClassMarkitdownParser
Markitdown file parser. Uses Microsoft's markitdown library to convert various file formats to markdown including PDF, Office docs, imag
hindsight-api-slim/hindsight_api/engine/parsers/markitdown.py:48
↓ 10 callersClassMockFile
hindsight-api-slim/tests/test_file_retain.py:533
↓ 10 callersClassRecordingPrecheckValidator
Validator that records every precheck call and can be configured to reject. Used to drive the FastAPI dependency that runs precheck() before body
hindsight-api-slim/tests/test_extensions.py:880
↓ 9 callersClassCancellationToken
A one-shot, cooperative cancellation signal. Cheap to poll (``raise_if_cancelled``) at stage boundaries and awaitable (``wait``) so a driver
hindsight-api-slim/hindsight_api/cancellation.py:47
↓ 9 callersClassConfigResult
Outcome of editing ``config.toml``. ``action`` is one of ``created``, ``merged``, ``unchanged``, ``removed``, or ``manual`` (file couldn't be
hindsight-integrations/openhands/hindsight_openhands/openhands_config.py:60
↓ 9 callersClassEntityResolver
Resolves entities to canonical IDs with disambiguation.
hindsight-api-slim/hindsight_api/engine/entity_resolver.py:95
↓ 9 callersClassLLMResponseUsage
Provider-reported token usage for the in-flight LLM call. Stashed by provider implementations as soon as a response is received — *before* lo
hindsight-api-slim/hindsight_api/engine/llm_trace.py:80
↓ 9 callersClassLLMStrategyConfig
How to route a request across the members of a multi-LLM chain. ``mode`` is "failover" (try members in order) or "round-robin" (rotate the st
hindsight-api-slim/hindsight_api/config.py:1409
↓ 9 callersClassMaintenanceLoop
Owns the single periodic maintenance task for a :class:`MemoryEngine`.
hindsight-api-slim/hindsight_api/engine/maintenance.py:54
↓ 9 callersClassOnnxEmbeddings
Local ONNX Runtime embeddings provider. This provider runs transformer embedding models in-process with ONNX Runtime, avoiding a sidecar Olla
hindsight-api-slim/hindsight_api/engine/embeddings.py:253
↓ 9 callersClassRetrievalResult
Result from a single retrieval method (semantic, BM25, graph, or temporal). This represents a raw result from the database query, before mer
hindsight-api-slim/hindsight_api/engine/search/types.py:32
↓ 9 callersClassTurnContext
Identity context extracted from an AgentCore Runtime invocation. This should be populated from trusted sources (validated JWT claims, AgentCo
hindsight-integrations/agentcore/hindsight_agentcore/bank.py:20
↓ 8 callersClassConfig
hindsight-api-slim/hindsight_api/engine/directives/models.py:36
↓ 8 callersClassCrossEncoderReranker
Neural reranking using a cross-encoder model. Configured via environment variables (see cross_encoder.py). Default local model is cross-
hindsight-api-slim/hindsight_api/engine/search/reranking.py:195
↓ 8 callersClassHindsightClient
HTTP client for the Hindsight API.
hindsight-integrations/cursor-cli/hindsight_cursor_cli/hooks/scripts/lib/client.py:43
↓ 8 callersClassHindsightStorage
CrewAI Storage backend that persists memories to Hindsight. Maps CrewAI's storage interface to Hindsight's memory API: - save(value, metadata
hindsight-integrations/crewai/hindsight_crewai/storage.py:29
↓ 8 callersClassMockChunk
hindsight-integrations/litellm/tests/test_integration.py:940
↓ 8 callersClassMockLLM
Mock LLM provider for testing. This provider records all calls and returns configurable mock responses, enabling tests to verify LLM int
hindsight-api-slim/hindsight_api/engine/providers/mock_llm.py:18
↓ 8 callersClassQueryAnalysis
Result of analyzing a natural language query. Contains extracted structured information like temporal constraints.
hindsight-api-slim/hindsight_api/engine/query_analyzer.py:37
↓ 8 callersClassReflectAgentResult
Result from the reflect agent.
hindsight-api-slim/hindsight_api/engine/reflect/models.py:109
next →1–100 of 2,579, ranked by callers