Search: bridge
Search MCP servers and agent skills by name, description, category or topic — 99 results.
NVIDIA/Megatron-Bridge/adding-model-support
Guide for adding support for new LLM or VLM models in Megatron-Bridge.
NVIDIA/Megatron-Bridge/build-and-dependency
Dev environment setup for Megatron Bridge — container-based development, uv package management, lockfile regeneration, adding dependencies, Slurm container usage, and common build...
NVIDIA/Megatron-Bridge/bump-dependency
Bump a pinned dependency (TransformerEngine, Megatron-LM, NRX, etc.), regenerate the lockfile, open a PR, and drive it to green by attaching a watchdog to the "CICD NeMo" workflow...
NVIDIA/Megatron-Bridge/cicd
CI/CD reference for Megatron Bridge — pipeline structure, commit and PR workflow, CI failure investigation, and common failure patterns.
NVIDIA/Megatron-Bridge/linting-and-formatting
Code style and quality rules for Megatron Bridge — ruff configuration, naming conventions, type hints, mypy rules, docstrings, copyright headers, logging, and the code review check...
NVIDIA/Megatron-Bridge/mlm-bridge-training
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data.
NVIDIA/Megatron-Bridge/multi-node-slurm
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures.
NVIDIA/Megatron-Bridge/nemo-rl-e2e-testing
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron poli...
NVIDIA/Megatron-Bridge/parity-testing
Structured framework for verifying numerical parity of HFMCore weight conversions.
NVIDIA/Megatron-Bridge/perf-activation-recompute
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
NVIDIA/Megatron-Bridge/perf-cpu-offloading
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
NVIDIA/Megatron-Bridge/perf-cuda-graphs
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
NVIDIA/Megatron-Bridge/perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as...
NVIDIA/Megatron-Bridge/perf-hierarchical-context-parallel
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
NVIDIA/Megatron-Bridge/perf-megatron-fsdp
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
NVIDIA/Megatron-Bridge/perf-memory-tuning
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.
NVIDIA/Megatron-Bridge/perf-moe-comm-overlap
MoE expert-parallel communication overlap in Megatron Bridge.
NVIDIA/Megatron-Bridge/perf-moe-dispatcher-selection
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
NVIDIA/Megatron-Bridge/perf-moe-hardware-configs
Representative MoE training playbooks by hardware platform and model family.
NVIDIA/Megatron-Bridge/perf-moe-long-context
Long-context MoE training guidance for Megatron Bridge.
NVIDIA/Megatron-Bridge/perf-moe-optimization-workflow
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
NVIDIA/Megatron-Bridge/perf-moe-vlm-training
Practical guidance for training MoE VLMs in Megatron Bridge.
NVIDIA/Megatron-Bridge/perf-parallelism-strategies
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
NVIDIA/Megatron-Bridge/perf-sequence-packing
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP...
NVIDIA/Megatron-Bridge/perf-tp-dp-comm-overlap
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
NVIDIA/Megatron-Bridge/recipe-recommender
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal.
NVIDIA/Megatron-Bridge/resiliency
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
NVIDIA/Megatron-Bridge/testing
Testing reference for Megatron Bridge — unit and functional test layout, tier semantics (L0/L1/L2/flaky), script conventions, running tests locally, adding/moving/disabling tests,...
NVIDIA/Megatron-Bridge/verl-e2e-testing
External verl end-to-end validation workflow for Megatron-Bridge model/provider changes.
longbridge/longbridge-mcp
Official Longbridge brokerage MCP — 110 tools for US/HK real-time quotes, options, trading, fundamentals, analyst ratings, calendars, price alerts, DCA plans, portfolio analytics and community sharelists. Hosted at `https://openapi.longbridge.com/mcp` with OAuth 2.1 via RFC 9728.
sshahzaiib/agy-bridge
Delegate heavy tasks from Claude Code (or any MCP client) to the Antigravity CLI (Gemini): file analysis, repo archaeology, web lookups, and adversarial second-opinion code reviews. Quota-aware model failover with cooldowns, per-tool timeouts, and multi-turn session continuity.
more-io/apple-bridges
Native macOS app access — manage Apple Reminders, Calendar, Contacts, Notes, Mail, and tmux sessions via Swift CLI bridges
muend/arcgis-mcp-bridge
Secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC, with worker-process isolation, PathGuard filesystem boundaries, and 100 geoprocessing tools.
huj28-creator/wechat-fastbridge
Token-efficient macOS WeChat MCP server for verified chat reading, text/file/sticker sending, fuzzy safe routing, smart context retrieval, and allowlisted live monitoring without screenshots or private-protocol access.
dashi96/chromium-bridge
MCP server + Chrome extension that connects Claude Code to Chromium-based browsers (Arc, Vivaldi, Brave) where the official Claude in Chrome extension doesn't work — navigate, click, read pages, run JS, and record GIFs in the user's real browser.
zzhang82/Agent-Memory-Bridge
MCP-native, local-first memory for coding agents that turns coding sessions into reusable engineering memory: decisions, gotchas, and domain knowledge.
Neverlow512/agent-droid-bridge
MCP server giving AI agents programmatic control over Android devices and emulators via ADB. 11 tools covering UI inspection, screen interaction, ADB commands, and change detection.
MakeaMouse/fish-bridge-mcp
Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.
hampsterx/claude-mcp-bridge
Wraps Claude Code CLI as MCP tools (query, search, structured, sessions) with subscription-first auth, cost metadata, budget caps, and granular tool sandboxing.
polsolbridge/solana-swap-api
Non-custodial crypto swap over MCP: Solana (Jupiter) + 7 EVM chains (KyberSwap), universal cross-chain router, Solana priority-fee oracle, and Hyperliquid perps. Returns unsigned transactions for your own wallet to sign — no API key, no KYC. Remote at https://swaptitan.net/mcp
butterlatte-zhang/unity-ai-bridge
Remote-control Unity Editor from any AI IDE via file-based IPC — 62 tools across 13 categories, zero dependencies, supports Claude Code, Cursor, Copilot, Windsurf, Claude Desktop.
jaspertvdm/mcp-server-gemini-bridge
Bridge to Google Gemini API. Access Gemini Pro and Flash models through MCP.
jaspertvdm/mcp-server-ollama-bridge
Bridge to local Ollama LLM server. Run Llama, Mistral, Qwen and other local models through MCP.
iprashantraj/mcp-discord-bridge
Discord MCP server with 46 tools for channels, messages, forums, webhooks, members, roles, threads, and moderation. Zero-install via `npx -y mcp-discord-bridge`. Also runs as a standalone bot with slash commands.
debridge-finance/debridge-mcp
Cross-chain swaps and bridging across EVM and Solana blockchains via the deBridge protocol. Enables AI agents to discover optimal routes, evaluate fees, and initiate non-custodial trades.
jaspertvdm/mcp-server-openai-bridge
Bridge to OpenAI API. Access GPT-4, GPT-4o and other OpenAI models through MCP.
ugurcl/dbridge-mcp
Query SQLite, PostgreSQL, and MySQL in plain language — read-only by design, with column hiding/masking, row caps, per-query timeouts, cost-based rejection, and rate limiting.
kenneives/design-token-bridge-mcp
Translates design tokens between platforms — extract from Tailwind, CSS, Figma, or W3C DTCG, then generate Material 3 (Kotlin), SwiftUI, Tailwind config, and CSS Variables with WCAG contrast validation.