Search

Agent Cache Runtime for building cache-aware LLM applications.

Track LLM costs across OpenAI, Anthropic, LangChain, and 2000+ models with zero code changes

AutoGen tools for the Ejentum Reasoning Harness. Four agent-callable async functions (harness_reasoning, harness_code, harness_anti_deception, harness_memory) returned by ejentum_tools(api_key=...). Each call retrieves a task-matched cognitive operation engineered in two layers: a natural-language procedure plus an executable reasoning topology.

LangChain integration for the Ejentum Reasoning Harness. Four BaseTool subclasses (reasoning, code, anti-deception, memory) an agent calls before generating. Each call returns a task-matched cognitive operation engineered in two layers: a natural-language procedure plus an executable reasoning topology (graph DAG with gates, parallel branches, and meta-cognitive exits).

Drop-in LangGraph integration for Neruva agent memory + reasoning substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LLM) + classify_intent_node / reflect_node factories for drop-in graph wiring. Plus NeruvaCheckpointSaver (BaseCheckpointSaver) + NeruvaContextStore (BaseStore) for graph state persistence. Substrate stays $0/call (pattern-C). Deterministic from seed. Works with every LangGraph StateGraph.

Agentic RAG over any PDF — grounded, cited answers from research reports, ESG/sustainability disclosures, contracts, manuals, and filings. Multi-agent LangGraph workflow with hybrid retrieval, RAPTOR summaries, NL→SQL over extracted tables, CRAG corrective loops, and a defense-in-depth hallucination stack.

LLM Guard scanners for AgentForge guardrails

Rule-first three-filter pipeline for cleaning unit-test training data, packaged as four SKILL.md skills.

Real-time URL trust scoring for AI agents

Stop waiting for your LLM to finish generating. agentic_json is a real-time streaming parser with a clean decorator API, letting your AI agents process and react to structured data mid-stream.

Generate DATABASE.md schema documentation for Django projects and LLM agents

PGate — Prompt ORM for LLM agents. Store, compile, validate and cache prompt contracts locally.

AI coding agent observability and causal tracing for Claude Code, Codex CLI, and OpenCode

Neondroplets Multi-Agent System (MAS) Platform CLI

Memplex - Memory Complex: multi-agent knowledge graph memory system with 3-layer retrieval

Exponential backoff with full jitter for LLM API calls. Sync + async. Built-in retryable-code presets for Anthropic, OpenAI, Bedrock, Gemini. Zero runtime deps.

Idempotency keys for LLM agent retries. Deterministic content-derived keys (sha256-hex, UUIDv5, scoped). Pairs with cachebench miss-aware retry. Zero runtime deps.

Truncate LLM tool output with head/tail/middle/middle_lines strategies. UTF-8 safe, zero runtime deps.

AI model: Agnuxo/Agente-Director-Qwen2-7B-Instruct_CODE_Python-Spanish_English_GGUF_q5_k

AI model: mradermacher/VeriOS-Agent-7B-GGUF