projectmind
Local installio.github.Nodemint-dev/projectmind
Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
2,177 servers in AI & Agents
Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.
Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.
Save AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.
Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
List agents, trigger workflows, and enforce team AI policies with ConductGuard.
Knowledge base for Claude Code with semantic search, feed intelligence, and teams
Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).
Read markdown with inlined images and index headings for agentic RAG workflows.
Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.
Pre-execution audit for autonomous agents. Independent receipt before irreversible actions.
Private encrypted agent messaging, hidden state exchange, delegation, and private inbox workflows.
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.
Local-first, source-backed continuity for AI agents via stdio MCP.
Hand a human a rich interactive UI by URL and get structured data back, from any MCP client.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.
Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence.
Local-first, source-traceable agent memory — no LLM at ingest, fully offline
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Makes any AI agent globally reachable and discoverable—no cloud, domain, or port forwarding needed.
Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing.
One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.
Self-maintaining knowledge vault: figure-level search, auto-wikilinks, and memory compression.