SanjoyDat1

Capability-token gate for AI agents. Mint time-boxed, scope-limited grants that authorize specific tool calls.

Enables AI agents to branch, score, prune, and merge conversation strands with provenance and timeline export. Provides MCP tools and resources for managing par

An MCP server that validates tool calls against JSON Schema, performs deterministic repair, redacts secrets, and maintains a hash-chained audit ledger.

Goal-oriented narrative state machine for AI agents, exposing live world/scene context as MCP tools and resources.

Enables AI agents to fork plans into counterfactual worlds, score them with rubrics and simulations, detect contradictions, measure regret, and merge a winner w

Evidence-weighted trust graph for multi-agent systems. Enables querying trust and gating high-risk actions based on time-decayed evidence and endorsements.

Headless, peer-to-peer context synchronization for local AI agents. It enables multiple LLM agents to share structured context and resolve state conflicts over

AI onboarding OS for startups providing handbook Q&A with citations, Day‑1/Week‑1 checklists, and readiness tracking via MCP tools.

Enables chain-of-thought reasoning with self-consistency voting, allowing sampling of diverse reasoning paths and aggregating answers via majority or weighted v

MCP server that parses stack traces and logs to generate deduplicated issue drafts with severity, repro steps, and owner guesses.

Enables generating AI-powered standups from git activity, with risk flags and markdown digests, via MCP tools.

MCP server implementing Chain-of-Verification to reduce LLM hallucinations by drafting answers, planning fact-check questions, answering them independently, and

MCP server implementing ReAct reasoning-acting loops with tools like search, lookup, and finish, supporting both fixture and OpenAI LLMs for offline-first, trac

MCP server for Tree-of-Thoughts search engine enabling deliberate problem solving with LLM agents via BFS, DFS, and beam search policies.

MCP server implementing the Generative Agents memory architecture, enabling observation, retrieval, reflection, and planning for agent memory management.

MCP-native TypeScript implementation of the Reflexion verbal RL loop for language agents, providing tools to start tasks, act, evaluate, reflect, and retry with

A lightweight MCP server implementing the GraphRAG pipeline for hierarchical knowledge graph construction and query-focused summarization.

Semantic caching MCP server for AI agent tool calls, providing exact and similarity-based cache lookup, store, invalidation, and metrics via MCP tools.