CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
razroo avatar

state-trace

razroo/state-trace
2STDIOregistry active
Summary

Bounded working memory for coding agents that need to remember what file failed, what hypothesis was already tried, and what to do next without burning your context window. Exposes typed graph nodes (task, observation, file, error_signature, patch_hunk) and edges (patches_file, supersedes, contradicts) instead of generic entity-relation pairs. Query current_state() to see what's live, failed_hypotheses() to avoid proposing the same fix twice, and retrieve_brief() to get compact file-level context for smaller models. Built on networkx with SQLite+FTS5 cold storage. Beats BM25 and Graphiti on SWE-bench-Verified artifact localization (25% vs 18% vs 10% at rank 1) with 15ms retrieval latency. Mount it via stdio MCP in Claude, Cursor, or any agent loop that needs memory with decay and compression baked in.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Lid closed, agents working
Lid closed, agents working
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distraction from your iPhone for freeBlock distraction from your iPhone for free
Block distraction from your iPhone for free
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →

Configuration

STATE_TRACE_STORAGE_PATH

Path to the SQLite or JSON file backing the working-memory graph. .db/.sqlite/.sqlite3 = SQLite (recommended); other = JSON. Defaults to ~/.state-trace/memory.db.

STATE_TRACE_NAMESPACE

Namespace to scope reads and writes (e.g. the repo slug). Nodes without a namespace remain visible to all namespaces.

STATE_TRACE_CAPACITY_LIMIT

Working-memory budget in capacity units. Default 256.

Categories
AI & LLM ToolsMonitoring & Observability
Registryactive
Packagestate-trace
TransportSTDIO
UpdatedApr 25, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
rbfinch avatar
Hindsight MCP

rbfinch/hindsight-mcp

MCP server for AI-assisted coding with development history: git, tests, Copilot.
2
revsmoke avatar
Promptrejectormcp

revsmoke/promptrejectormcp

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
2
sou0327 avatar
Knowmint

sou0327/knowmint

AI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.
2
szara7678 avatar
OpenAkashic

szara7678/openakashic

Shared long-term memory vault for AI agents with 20 MCP tools.
2
thezenmonster avatar
agentmem

thezenmonster/agentmem

Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
2
tjp2021 avatar
Mcp Thinkgate

tjp2021/mcp-thinkgate

Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.
2