Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.
| Date | Stars |
|---|---|
| 2026-07-31 | 267 |
| 2026-08-06 | 269 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Argus Agent **Local memory. Hybrid retrieval. Self-correcting reasoning. Benchmark-grade recall.** Argus Agent is a memory-first AI agent for long-context personal intelligence, grounded recall, temporal reasoning, quantitative reasoning, and tool use. It is designed as an open, inspectable alternative to memory agents such as Hermes or OpenClaw, with a stronger emphasis on durable local memory, strict attribution, self-correcting retrieval, and benchmark-grade long-term recall. The current local implementation keeps normal semantic, episodic, and procedural learning in `agent.py`. Deterministic structured-artifact extractor code exists in the repo, but it is disabled in the active learning path while benchmark memory quality is being tuned. Local LongMemEval-S reports are checkpoints while learning and generation behavior is being validated. Treat checked-in report files as local progress snapshots, not final published benchmark numbers. Benchmark cost warning: a full 500-question LongMemEval-S run with the current model mix has cost about `$2,500` in practice, or about `$5` per average question. Run a 1-question or small-sample benchmark first before starting the full dataset. ## Contents - [Why Argus Exists](#why-argus-exists) - [What's New In v0.5.0](#whats-new-in-v050) - [What Makes It Different](#what-makes-it-different) - [Highlights](#highlights) - [Architecture](#architecture) - [Memory System](#memory-system) - [Structured Artifact Extractors](#structured-artifact-extractors) - [Local Storage Layout](#local-storage-layout) - [Retrieval Pipeline](#retrieval-pipeline) - [Temporal Reasoning](#temporal-reasoning) - [Quantitative Reasoning](#quantitative-reasoning) - [Self-Correcting Retrieval](#self-correcting-retrieval) - [Learning Pipeline](#learning-pipeline) - [Tool System](#tool-system) - [Coding Agent Delegation](#coding-agent-delegation) - [Benchmarks](#benchmarks) - [Benchmark Cost Planning](#benchmark-cost-planning) - [Current Local Metrics](#current-local-metrics) - [Requirements](#requirements) - [Quick Start](#quick-start) - [Control Console](#control-console) - [Agent Identity Config](#agent-identity-config) - [Channel Integrations](#channel-integrations) - [API Job Queue](#api-job-queue) - [Environment Variables](#environment-variables) - [Repository Map](#repository-map) - [Design Principles](#design-principles) - [Status](#status) - [License](#license) ## Why Argus Exists Most agents can chat. Fewer can remember. Almost none can remember carefully. Argus Agent is built around a simple idea: memory is not just vector search. A serious memory agent needs to know what a memory means, when it happened, what numbers belong to, which entity a fact is attached to, when evidence is incomplete, and when it must search again instead of guessing. Argus combines: - local FAISS vector memory - semantic, episodic, and procedural memory separation - hybrid vector plus keyword retrieval - HyDE-style query expansion - dynamic recall depth - strict temporal grounding - numeric attribution and exact aggregation rules - structured artifact extractor code for table rows, lists, blocks, quotes, budgets, timelines, metrics, ratios, and other evidence-shaped outputs, currently disabled in the active learning path - self-correcting fallback retrieval - background memory consolidation - LangGraph orchestration - progressive tool routing The result is an agent that behaves less like a stateless chatbot and more like a disciplined cognitive system. ## What's New In v0.5.0 This release turns Argus into a much more complete local agent runtime: - **Triage-first normal runtime:** normal chat now starts with a fast LLM triage layer that chooses direct response, tool routing, memory retrieval, or retrieval-before-tools. Information-only updates and questions already answerable from recent chat can skip foreground retrieval entirely. - **Benchmark path preserved:** benchmark traffic still uses the original retrieval, to
Excerpt of 54,862 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:cf0bdae644ba13b3, llm:Repository description: "A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools."
matched fp:cf0bdae644ba13b3, llm:Repository description: "A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools."
matched fp:cf0bdae644ba13b3, llm:Repository description: "A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools."