- Selvedge @masondelan/selvedgePersistent decision memory for AI coding agents: rationale, rejected approaches, and entity history.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Delimit — Keep the state. Change the model. @delimit-ai/delimit-mcp-serverKeep the state. Change the model. Shared context and a multi-model panel across coding assistants.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- World Model @saravananjaichandar/world-model-mcpTemporal knowledge graph for codebases with constraint enforcement at the edit boundary.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.23 GitHub stars.
- Pituitary @dusk-network/pituitaryCatch spec drift before it catches you. Detect overlap, stale docs, and code drift.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.22 GitHub stars.
- rag-rat @cq27-dev/rag-ratRepository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.22 GitHub stars.
- Kivgraph @luqueee/kivgraphCross-repository semantic code intelligence for AI coding agents, from a local code graph.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.21 GitHub stars.
- FixMap @aryamthecodebreaker/fixmapDeterministic local-first context and impact maps for coding agents from tasks, issues, and diffs.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Omen @panbanda/omenMulti-language code analysis for complexity, debt, hotspots, ownership, and defect prediction4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.21 GitHub stars.
- M1nd @maxkle1nz/m1ndThe shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- CodeMap @bbajt/codemap-mcpRoslyn-powered MCP server for C#/VB.NET. Query symbols, call graphs, and facts. 90%+ token savings.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.21 GitHub stars.
- Memory Journal @neverinfamous/memory-journal-mcpDeveloper journal with knowledge graphs, relationships, Git context, and semantic search4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.20 GitHub stars.
- Madar @mohanagy/madarAuthenticated local evidence paths for JavaScript and TypeScript coding agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- Instagit @instagitai/instagitMCP server for Instagit — AI-powered Git repository analysis for coding agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- Context Foundry @context-foundry/context-foundryRecursive Claude spawning for autonomous project builds with self-healing test loops8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- Knowing @blackwell-systems/knowingContent-addressed code graph with 22 MCP tools for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- DOS — the trust substrate for agent fleets @anthony-chaudhary/dos-kernelVerify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- Maple @maple-kit/mapleReview comments pinned to a running frontend, read and resolved by your coding agent.Not assessed yet.Runs on your machine, installed from npm.19 GitHub stars.
- adrkit decision memory @adrkit/mcpDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Ekbasis @openinterpretability/ekbasisForesee what git commands and multi-step changes will do, as calibrated probabilities3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.18 GitHub stars.
- GitWarren @klarluft/gitwarrenCode review on your own machine, for you and your coding agent. Nothing leaves your computer.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- CommitLore @monglong0214/commitloreGit-native decision memory for coding agents: only the decisions still in force for the edited path5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.18 GitHub stars.
- OrangePro @orangepro/mcpFind test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Agentpack @ihorponom/agentpackRepo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Cortex @danielblomma/cortexLocal repo context for coding assistants with semantic search and graph relationships.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
