Awesome Memory Papers in Vision-Language Models
-
Updated
Aug 24, 2026
Awesome Memory Papers in Vision-Language Models
An AI partner with true active memory. She keeps a diary in her own voice, digests her days in nightly dreams, knows what today is, and comes back tomorrow remembering the life you share. Voice, desktop avatar (Live2D / VRM / three.js / html vanilla), a multi-layered self. Companionship is one use case; the memory is the point. Runs on Claude Code.
LLM-agnostic memory layer for AI agents. No embeddings, no vector DB — just fast, structured, temporal memory that any LLM can consume as plain text.
Local-first cross-session memory for DeepSeek Harness (DSH): automatic capture, Event/Element cards, evidence-gated recall, source tracing. 本地跨会话长期记忆。
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
HipCortex is a persistent, local causal memory engine solving context-loss and token inefficiency in AI agents. It stores decisions as a causal graph served via HTTP/MCP, replacing bloated chat histories with lean context. This symbolic memory enables reasoning-capable architectures that retain knowledge across sessions.
ForeSight: a temporal-aspect long-term memory plugin for DeepSeek Harness (dsh)
A lightweight, pluggable memory backend for agent-based simulations. Supports temporal data, experience replay, and persistent state logging
A memory your coding assistant can search, kept in one file on your disk. It knows when a fact was true and where it came from. No server, nothing uploaded.
Durable, private, time-aware memory engine for long-running AI agents
Temporal verification firewall for coding agents, backed by CockroachDB and AWS.
Local-first memory kernel for coding agents: MCP-native, temporal, auditable, source-keyed, and benchmarked.
Sovereign context, memory and provenance infrastructure for AI agents. Bitemporal knowledge, evidence and decision lineage, delivered to any agent over the EPCTX/1 protocol (SDK/REST/MCP). Local-first, zero-egress, no mandatory LLM. MIT.
Turn saved discoveries into local, project-aware memory for AI agents.
Time-aware memory system that understands when things happened, not just what happened
Offline-first deterministic agent harness with GraphRAG, temporal memory, DoT DAG planning, and SLM/LLM routing.
Sellmind - Temporal Memory for AI. Cross-session memory persistence with emotional coherence. Built for Claude Code agents.
Autopilot durable local operating system for Hermes and cooperating AI agents. SQLite execution truth, shared memory, temporal facts, recovery, and handoffs.
Add a description, image, and links to the temporal-memory topic page so that developers can more easily learn about it.
To associate your repository with the temporal-memory topic, visit your repo's landing page and select "manage topics."