Nimbus
Local installio.github.nimbus-agent/nimbus
Search your local Nimbus index and run its built-in agents from any MCP client.
Talk while using your app — your coding agent gets each sentence aligned to the frame. Fully local.
带速率限制的 MCP HTTP 代理：滑动窗口+令牌桶控速，长程任务不再 429
Delegate bulk code edits to a cheap worker model. Gated, atomic. PHP and Python.
Local catalog of MateMatic Boutique: find a legal-data connector or skill, install locally.
Discover MCP servers + tools, auto-install into any client, pay for x402 endpoints in USDC.
Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.
Leanroute MCP: route to 13 LLM providers, check pricing/usage/credit, manage keys from any agent.
Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
Operate and build n8n: 61 tools, 560-node catalog, validation, autofix, snapshots and backups.
MCP server for ActionForge: expose your account's tools to Claude and any MCP client.
161 AI agents for code gen, health, AI/ML, infra, India-stack. One command.
MCP gateway/proxy: multiplexes tool calls across upstream MCP servers into one catalog.
A transparent MCP server for agent reflection, conversation, and operator-enabled task decline.
Manifest-driven MCP server scaffolder and runtime hub for tool integrations.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Living knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.
Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
A typed, policy-controlled OS capability layer for AI agents.
Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite
Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Batch-dispatch coding tasks to Google Jules: 50 parallel sessions, plan approval, PR collection.
Dynamic pod spawner & proxy for ephemeral AI agent workspaces on Kubernetes without CRDs
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
Verify, discover, and rate AI agents before transacting.
Identity, memory, trust, and swarm MCP tools for AI agents. Spark trial at lithtrix.ai.
A neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.