Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Showing 1,105–1,152 of 2,642
The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.
SwarmDM (formerly AgoraDM): DMs, friends, groups and files between AI agents.
Private, portable memory and reusable skills for AI agents.
Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).
Repair malformed JSON from LLM/agent output; optional JSON Schema coercion. Free + x402 paid.
Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.
See each coding-agent subscription's live limits and offload work to one with headroom.
Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.
AI image generation and editing MCP server. Gemini + OpenAI, iterative editing, undo/redo.
Read-only session finder across coding-agent harnesses: search, page prompts, hand off.
Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Search and browse every MCP server in the Model Context Protocol registry.
Brand visibility auditing across LLMs, AI search, and answer engines with GEO reports and scores.
Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
Structured thinking + steel-manning verification for AI agents. Backed by 43+ papers.
Account-less MCP access to 45 Gemini models & autonomous agents via L402, x402, and MPP.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
AI memory buyer routing with Forge docs, pricing, paid recommendations, and MCP discovery.
Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation
Interaction profile registry for AI agents. Log interactions, query behavioral lenses.
Plain-English training-data scout: 12 experts sweep HuggingFace + GitHub, compose scored packs.
Cross-session WebFetch cache for Claude Code. Unlimited TTL by default, SQLite, MCP plugin.
MCP server for Sber SaluteSpeech API — speech recognition and synthesis.
Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.
Agent 知识共享市场 — 让 AI Agent 搜索/购买/上传经验记忆。34 个 Tools，支持记忆搜索、购买、上传、评价、团队协作。
Give your bot an identity!
Local-first memory system for AI agents with hybrid search and graph reasoning
MCP server providing access to 300+ AI models via OpenRouter
Local, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.
MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)
Find an MCP server for any task: searches the official registry, Smithery and npm; remote-first.
Session handoff for Claude Code: list sessions and build handoff docs another agent continues from.
Local multi-client RAG server over the Model Context Protocol.
Persistent memory for AI assistants. Store, search, and recall across sessions.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
Local-first memory for AI agents: facts with hash-chain provenance, verified recall.
Signed, sealed handoffs between AI agents — trust computed by the receiver.
Public broadcast and durable shared memory for AI systems and agents using signed Events.
Search MCP servers, agent skills and AI tools by task. Read-only, no API key.
Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
Local-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown.
A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.
Exact, durable handoffs between AI coding agents: one turn in the right session, never twice.
