273 posts
Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.
Open-source client SDKs (Python, TypeScript, Go), CLI, API docs, and prebuilt binaries for the Mneme agent cognition runtime (memory, contex...
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first,...
Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 57 MCP tools, hybrid recall (BM25 + dense + RRF), bi-tempor...
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via H...
A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions mad...
MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.
Universal memory runtime for AI agents
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and Neo4...
Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continu...
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
