AIOS — a local-first memory layer for AI agents. Your agents learn from every run and carry forward what worked, across Claude Code / Codex / any MCP client. White-box, draft-first, with published evals. Install as a Claude Code plugin in 2 commands.
- capability exposure inferred + 4
- recent drift inferred + 12
- tool safety inferred + 12
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 2m ago · see ecosystem CVEs →
- A · 4 → B · 28
- C · 35 → A · 4
No known CVEs for this server.
- high dangerous code
committed secret: OpenAI key
analyzed commit a49332b · analyzer v28 · 2h ago
skills & prompt files 26
- skill cjw0076-myworld-a49332b/.claude/skills/absorption-probe/SKILL.md
- skill cjw0076-myworld-a49332b/.claude/skills/aios-decide/SKILL.md
- skill cjw0076-myworld-a49332b/.claude/skills/aios-memory-propose/SKILL.md
- skill cjw0076-myworld-a49332b/.claude/skills/local-llm-agent/SKILL.md
- skill cjw0076-myworld-a49332b/.claude/skills/multi-substrate-review/SKILL.md
- agent-rules cjw0076-myworld-a49332b/AGENTS.md
- agent-rules cjw0076-myworld-a49332b/CLAUDE.md
- agent-rules cjw0076-myworld-a49332b/tests/fixtures/project_discovery/workspace/project_alpha/AGENTS.md
- agent-rules cjw0076-myworld-a49332b/tests/fixtures/project_discovery/workspace/project_beta/CLAUDE.md
- agent-rules cjw0076-myworld-a49332b/tests/fixtures/project_discovery/workspace/project_conflict/AGENTS.md
- agent-rules cjw0076-myworld-a49332b/tests/fixtures/project_discovery/workspace/project_secret/AGENTS.md
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface/prompts/leaf_consumer.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface/prompts/leaf_producer.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface/prompts/whole.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface_contract/prompts/leaf_consumer.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface_contract/prompts/leaf_producer.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_iface_contract/prompts/whole.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/leaf_aggregate.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/leaf_filter.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/leaf_format.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/leaf_parse.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/leaf_transform.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/coding_pipeline/prompts/whole.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/lean_compose/prompts/leaf_p0.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/lean_compose/prompts/leaf_p1.txt
- prompt-file cjw0076-myworld-a49332b/tests/hivemind_tasks/lean_compose/prompts/whole.txt
danger signals3
- suspicious endpoint api.telegram.org cjw0076-myworld-a49332b/scripts/aios_channel.py :168
_TELEGRAM_API = "https://api.telegram.org/bot{token}/{method}" - suspicious endpoint 169.254.169.254 (cloud metadata) cjw0076-myworld-a49332b/tests/test_aios_endpoint_policy.py :29
self.assertFalse(p.is_allowed("http://169.254.169.254/latest/meta-data")) # cloud metadata - committed secret OpenAI key cjw0076-myworld-a49332b/tests/test_aios_serving_support.py :214
sk-sec…(24 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:cjw0076/myworld/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of cjw0076.