Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.
Repo-native shared memory for AI coding agents.
First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
European memory system for AI agents with focus on compression and weighted information
Memory that degrades gracefully — four-tier lifecycle memory for AI agents
Governed, GDPR-native memory for AI agents with ITSM / ServiceNow integration built in: right-to-erasure, tenant isolation, prompt-injection defense, and audit. A governance layer over Mem0, Zep, or any store. Open-source alternative for compliant AI agent memory.
Local-first knowledge framework with source-grounded provenance. Every fact cites its exact origin.
Get started with Novyx Core in 5 minutes
A self-hosted AI companion exploring evolving relationship memory, initiative, and cross-device context.
Persistent semantic state engine for AI agents — knowledge graphs, dynamic RAG, semantic zoom, bidirectional natural language translation, provenance tracking, self-extending graph.
Local-only decision log for AI agent sessions -- zero API calls, deterministic decision extraction.
Persistent session memory for Claude Code and OpenAI Codex. Capture, recall, and sync AI coding sessions as private Markdown in Git—no database or daemon.
An MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.
Five runnable demos for building resilient AI agents with Strands Agents: chaos-test the agent's tools, gate memory writes to stop hallucinations, defend against memory poisoning and prompt injection, verify multi-step tasks against the backend, and let an agent write its own tools. Runs on OpenAI or Amazon Bedrock.
Verifiable state plane for autonomous agents: memory, belief revision, rollback, audit, and MCP tools.
Context hygiene for agentic coding. Save and resume Claude Code/Codex sessions.
To associate your repository with the ai-agent-memory topic, visit your repo's landing page and select "manage topics."