- mdflow — Context OS for AI Coding Agents @yubinbin32-ops/mdflowContext OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.12 GitHub stars.
- Memex @stifler7/memexTemporal engineering context for agents via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- thread-keeper @po4erk91/thread-keeperMulti-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- ContextOS — Powered Exoskeleton for AI Coding @yubinbin32-ops/contextosContext exoskeleton for AI development: reduce token usage and context occupancy.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.11 GitHub stars.
- trovex @tsukumohq/trovexServes coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Lockstep @lockstep-team-agent/lockstepDecision memory for AI coding agents: captures decisions once, briefs every agent before it acts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- magents @abnegate/magentsShared session bus MCP+CLI for Claude/Codex/Cursor/Grok: list, read, handoff, send, spawn.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.10 GitHub stars.
- KLYPIX Project Brain @dahshanlabs/klypix-mcpActive state management for multi-agent coding: a shared, versioned project brain over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- Causari @croviatrust/causariRecords the prompt, model and files an agent declared for a line. It does not prove who typed it.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.9 GitHub stars.
- PromptBranch @promptbranch/promptbranchLocal-first MCP server for versioning, searching, evaluating, and improving AI prompts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- redcon @natiixnt/redconDeterministic context packing for AI coding agents; measured 83% fewer input tokens, local.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Sophon @lacausecrypto/sophonHonest token economics for MCP agents. 68% tokens saved, zero-ML Rust binary.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Strategy Skills @eterdis/strategy-skills11 open strategy frameworks as AI-guided prompts for any MCP client.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Context @alex-feel/mcp-context-serverAn MCP server that provides persistent multimodal context storage for LLM agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Dossier @imboard/dossierMCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Unified AI System MCP Gateway @happy520ai/unified-ai-systemSelf-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- AI Context Kit @ofershap/ai-context-kitLint, measure, and sync AI context files across Cursor, Claude Code, Copilot.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Codeledger @codeledgerecf/codeledgerDeterministic context selection for AI coding agents. Local memory that compounds across sessions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- ContextAtlas @traviswye/contextatlasPre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Tiger Skills @timescale/tiger-skillsProvider agnostic skills implementation, with skills sourced from local paths or GitHub repositories4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Mindswap @shiporbleed/mindswapLocal-first AI context and memory server for cross-tool coding continuity.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Skills Anywhere @noteflowai/dsh-skills-anywhereDiscover and load Agent Skills from configured local directories and Git sources over stdio MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- slivingdoc @baalimago/slivingdocDurable context for agents and people: shared notes with Git-style merges, no silent overwrites.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Portkey Admin @codeswhat/portkey-admin-mcpPortkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
