Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Hindsight Api

CLI Verifiziert Aktiv

Hindsight: Agent Memory That Learns

Zweck

To equip AI agents with sophisticated, persistent memory that mimics human recall, enabling better contextual understanding and reasoning over time.

Funktionen

Persistent memory for AI agents
Temporal, semantic, and entity-based recall
Support for multiple LLM providers
Python SDK for programmatic access
Configurable disposition traits for opinion formation

Anwendungsfälle

Building AI agents that need to remember past interactions and facts
Developing conversational AI that maintains context over long periods
Creating agents that can reason about events based on their temporal order
Enhancing agent capabilities with structured knowledge representation

Nicht-Ziele

Acting as a general-purpose database
Replacing the core LLM reasoning capabilities
Providing a front-end UI for end-users

Invocation

info:Hierarchical discoverable argumentsThe CLI provides a few top-level commands, but it is not a deeply hierarchical structure. The `--help` flag is available for each command.

Qualitätspunktzahl

Verifiziert

96 /100

Analysiert 13 days ago

Vertrauenssignale

Letzter Commit13 days ago

GitHub-Inhaber vectorize-io

Sterne13.2k

LizenzMIT

Websitehindsight.vectorize.io

Status

Quellcode ansehen

Ähnliche Erweiterungen

Pipelock

Open-source KI-Agenten-Firewall für MCP-Sicherheit: Agent-Egress-Kontrolle, DLP, SSRF und Schutz vor Prompt Injection.

luckyPipewrench

@codeharbor/agent Playbook

Local skill manager and installer for agent-playbook across Claude Code, Codex, and Gemini.

Speclock Ros2

AI Constraint Engine — erzwingt Regeln aus CLAUDE.md, .cursorrules, AGENTS.md als Gesetze. 51 MCP-Tools, 991 Tests. Offizielles MCP-Repository. npx speclock protect