AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Vision / Multimodal/
atlas
atlas logo

atlas

Active·★ 47·NOASSERTION·Updated 2026-05-02
★ Trending★ Workflow Automation★ Vision / Multimodal

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.

Atlas is an open-source local-first cognitive memory system that implements AGM-compliant belief revision on a property graph. It adds a propagation engine called Ripple that recomputes downstream beliefs when an upstream fact changes. The system runs entirely on your laptop and includes a hash-chained ledger, continuous ingestion from multiple sources, and API surfaces for integration.

#agm#ai-agents#anthropic#apache-2#belief-revision#claude-code#cognitive-memory#fastapi
$ Install
$ git clone https://github.com/RichSchefren/atlas && cd atlas && docker compose up -d && python3 -m venv .venv && source .venv/bin/activate && pip install -e ".[dev]"
↗ Visit site★ GitHub
01

Features

01AGM-compliant belief revision (49/49 postulates verified)
02Ripple propagation engine for downstream belief reassessment
03Hash-chained SHA-256 ledger with tamper detection
04Continuous ingestion from 6 streams (Obsidian, Limitless, Screenpipe, etc.)
05MCP, HTTP, and gRPC API surfaces with adapters for agent runtimes
02

Compatibility

macOS
macOS
Verified via docs
Linux
Linux
Verified via docs
Windows
Windows (WSL)
Verified via docs
03

Quick start

1
$ git clone https://github.com/RichSchefren/atlas
2
$ cd atlas
3
$ docker compose up -d
4
$ python3 -m venv .venv
5
$ source .venv/bin/activate
6
$ pip install -e ".[dev]"
04

Use cases

↳Pricing change invalidates positioning: updating a program price triggers reassessment of all value claims that depended on the old price.
↳Partner or person status change: a team member leaving triggers confidence drops in decisions and commitments that depended on them.
↳Deadline slips: a milestone moving weeks later triggers re-evaluation of all downstream project beliefs and contradictions.
05

Alternatives

ragflow logo
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
vs →
n8n logo
n8n★ 190.2k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
vs →
context-mode logo
context-mode★ 16.0k
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
vs →
Auto-claude-code-research-in-sleep logo
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
vs →
agents-best-practices logo
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
vs →
holaOS logo
holaOS★ 5.4k
The agent environment for long-horizon work, continuity, and self-evolution.
vs →
awesome-claude logo
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
vs →
initrunner logo
initrunner★ 38
Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
vs →
See all alternatives →

Related searches

atlas AlternativesBest Vision / Multimodal Tools 2026Open Source Vision / Multimodalatlas Tutorialatlas Vs Competitorsagmai-agentsanthropic

Comments

Log in to leave a comment
  • R
    Robin KimMay 22, 2026

    Used for research agent workflows where factual consistency over time matters

  • Quinn Chen
    Quinn ChenMay 13, 2026

    Local-first cognitive memory that actually handles contradictory beliefs gracefully

  • Blake Lee
    Blake LeeMar 5, 2026

    The belief revision formalism produces more coherent long-term agent behavior

  • O
    Oaklyn ThompsonMar 4, 2026

    AGM-compliant belief revision with 49/49 passing tests is a strong correctness claim

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Stats
GitHub Stars★ 47
Last commit4w ago
StatusActive
LicenseNOASSERTION
CategoryVision / Multimodal
Trend (30d)
+1.8↑ 0.7%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.