Autonomous AI agents that perform tasks independently
Agentic Purchase Order Intelligence — multi-agent document extraction with visual grounding and schema memory.
GitHub Actions
Agent-friendly API for DOCX document review — read, comment, propose changes, accept/reject tracked changes
timoaus
Platform-agnostic runtime for building conversational AI agents on Cloudflare Workers. Provides `AgentDO`, the `defineAgent` factory, session storage, capability lifecycle, scheduling, A2A, MCP, transport, and the channels primitives described below. See
...moreStructured output for any LLM call. Validate-and-retry loop for JSON responses; BYO LLM and validator. Python port of @mukundakatta/agentcast.
...moreValidate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises ToolArgError with LLM-friendly retry hint. Python port of @mukundakatta/agentvet.
...moreFit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers. Python port of @mukundakatta/agentfit.
...morelogikonline
Neo3 blockchain anchor for ADP calibration snapshots. Optional extension to @ai-manifests/adp-agent that periodically commits signed calibration snapshots to a Neo3-compatible chain.
...morezeeland
Scaffolding tool for creating new Rudder plugins.
petukhovart
CLI tool for visual verification of desktop apps (Electron/Tauri) via Chrome DevTools Protocol
symerian
SymiGhost — Red team AI agent gateway
dudenpc
Multi-strategy reasoning for AI agents — ReAct, Chain-of-Thought, Tree-of-Thought with HuggingFace SmolAgents and OpenAI-compatible backends. Built for Bottensor.
...moreAgentCard v1.0 adapters for LangChain, CrewAI, and AutoGen
Sanitize LLM outputs before HTML, SQL, shell, or markdown sinks. Python port of @mukundakatta/llm-output-sanitizer.
Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.
...moreEstimate hallucination risk in LLM answers from uncertainty language, unsupported specifics, citations, and context coverage. Python port of @mukundakatta/hallucination-risk-meter.
...moreDetect flaky LLM eval cases across repeated runs. Pass-rate + standard-deviation per case, with per-case severity. Python port of @mukundakatta/eval-flake-detector.
...moreStable semantic cache keys for LLM requests. Invariant to whitespace, casing, and key ordering; sensitive to model swaps, tool list, and retrieval context. Python port of @mukundakatta/semantic-cache-key.
...moreScore (query, document) pairs for vector/RAG poisoning signals: vector-text mismatch, instruction-like payloads, NaN, suspiciously round numbers. Python port of @mukundakatta/vector-poison-score.
...moreHeuristic quality metrics for RAG retrieval and grounded answers. Python port of @mukundakatta/rag-quality-kit.
Stryda
Stryda governance as a LangGraph node — plug it between the agent LLM and the tool executor.
Philipp Flotho
Local Python access to OAuth-authenticated Codex and Claude Code agents
Stryda
Drop Stryda governance into a LangChain agent — wrap a BaseTool, or attach a callback to an AgentExecutor.
Estimate LLM request cost and enforce per-request or per-session budgets. Python port of @mukundakatta/llm-cost-guard.
Devendra
LangChain toolkit for reliable Web3 execution via KeeperHub