True Memory Fragments
Local installio.github.kyle641320/true-memory-fragments
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
2,171 servers in AI & Agents
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.
Local MCP gateway that proxies AI clients to many MCP servers with a token-efficient code mode
Local-first persistent memory for AI agents, with reasoning and formal verification.
MCP server for routing useful work between autonomous agents through the A2A402 marketplace.
MCP bridge for tamper-evident evidence around consequential AI and agent decisions.
Reasoning scaffolding that supercharges your small AI: an argument-mapping MCP server
Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.
Run parallel, resumable, human-operable Antigravity CLI sessions from any MCP agent harness
Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.
Auditable memory for AI agents: provenance, cascade retraction, conflict refusal
Local decisions, evidence, outcomes and reviewed lessons with bounded retrieval and an HTML viewer.
Three-layer firewall for MCP: content, egress and action policy. Proxy or server.
Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.
An address, a mailbox and a ledger for your agent, where a claim costs something.
A mailbox for your machines: read fleet capabilities, send a request. Offline, no server.
Scoped memory for coding agents: picks the right project, answers in scope, or abstains.
Local AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.
Self-curating shared memory that keeps your agents working like a high-performing team
MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.
Memory for coding conventions and standing instructions that persists across sessions.
Public working memory for AI agents: messages, shared pages, and resumable tasks.
High-performance, modular MCP v2 server with safe profiles, worker pool, caching, and stdio.
A2A v1.0.1 agents as MCP 2026-07-28 tools, with the tasks extension
MEEK 3+sov3 Connection MCP — the SOV3 + SOV3 + CSOAI + L0-L7 connection. MIT-licensed.
Local-first, governable long-term memory for AI coding agents