{"data":{"slug":"winstonkoh87-athena-public","name":"Athena-Public","tagline":"The Linux OS for AI Agents","github_url":"https://github.com/winstonkoh87/Athena-Public","owner":"winstonkoh87","repo":"Athena-Public","owner_avatar_url":"https://avatars.githubusercontent.com/u/250412518?v=4","primary_language":"Python","stars":589,"forks":77,"topics":["ai","ai-agents","ai-assistant","automation","chatgpt","developer-tools","framework","gemini","google-antigravity","graphrag","knowledge-management","llm","local-first","memory","open-source","prompt-engineering","python","rag","semantic-search","vector-search"],"archived":false,"github_pushed_at":"2026-09-19T21:15:15+00:00","maintenance_label":"Very active","stars_delta_30d":46,"url":"https://www.graphcanon.com/tools/winstonkoh87-athena-public","markdown_url":"https://www.graphcanon.com/tools/winstonkoh87-athena-public.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/winstonkoh87-athena-public","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=winstonkoh87-athena-public","description":"Athena is a local-first agentic PKM that helps you make better decisions with your own context — persistent memory, structured reasoning, and governed AI agents that work across any LLM. Own the state. Rent the intelligence.","homepage_url":"https://winstonkoh87.com/athena/","license":"MIT","open_issues":0,"watchers":5,"ai_summary":"Persistent memory, structured reasoning, and governed autonomy for any LLM.","readme_excerpt":"### 3. Install the SDK *(optional — enables CLI commands)*\n\n```bash\n\n---\n\n# Lightweight install (~30 seconds, no ML dependencies)\npip install -e .\n\n---\n\n# Full install (~5–10 min, enables vector search and reranking)\npip install -e \".[full]\"\n```\n\n> ⚠️ **Don't `pip install athena-cli`** — that's a different, unrelated package. Always install from inside the cloned repo.\n\n---\n\n## 💰 Cost\n\n**Athena is free. Forever. MIT licensed.** You only pay for the AI subscription you're probably already paying for.\n\n| Plan | Cost | Who It's For |\n|:-----|:-----|:-------------|\n| **Google Antigravity (free tier)** | **$0** | **Try Athena first** — included with any Google account (Pro available at reduced quota) |\n| Claude Pro / Google AI Pro | ~$20/mo | Daily users — the sweet spot for most people |\n| Claude Max / Google AI Ultra | $100–$200/mo | Power users managing multiple domains (8+ hrs/day) — Max 5x $100, Max 20x $200, Ultra $100/$200 tiers |\n\n> **Try before you buy.** Athena works with Google Antigravity's free tier — clone the repo, type `/start`, and see if it clicks. No credit card, no trial period, no catch. The free tier includes Pro models at reduced quota — enough to evaluate whether Athena works for you. Upgrade when you need higher throughput.\n\n> **Why $200/mo sounds expensive — until you do the math.** A single employee costs $5,000+/mo in salary, benefits, and management overhead. An AI agent on a max-tier subscription costs $200/mo, works 24/7, doesn't call in sick, and scales to any domain you throw at it. For best results, subscribe to the max plan on any one platform (Claude Max, Google AI Ultra, etc.) — the difference between $20/mo and $200/mo is the difference between a tool you use occasionally and a tool that runs your life. Heavy users routinely consume $2K–$3K+ in equivalent API costs per month — the flat subscription turns variable cost into fixed cost. **For quota-limited plans** (which is now the norm — Google has tightened rate limits significantly since April 2026), use `/minmax` mode to maximize output quality per token — the MinMax doctrine maintains the same quality floor while reducing token consumption by ~74%. \n\n> **For peak performance, use `/ultrastart` every session.** On a flat-rate plan, the marginal cost of deeper thinking is $0 — so the cost of under-thinking always exceeds the cost of over-thinking. `/ultrastart` loads ~20K tokens of structured context (identity, canonical memory, active state, semantic bridge) every session. On API pricing, this costs $2–5/session. On a $200/mo flat plan, it costs nothing. **However:** on quota-limited plans (most plans since Apr 2026), Athena defaults to `/start` (~10K tokens) with the MinMax protocol, reserving `/ultrastart` for high-complexity sessions. The pricing model of the underlying compute layer directly determines Athena's performance ceiling.\n\n> Boot cost is 2K–20K tokens (depending on mode) — constant whether it's session 1 or session 10,000. [Details →](docs/BENCHMARKS.md)\n\n> [!NOTE]\n> Athena works with any model, but governance protocols and multi-step reasoning perform best with frontier models (e.g. Claude Fable 5, Gemini 3.5 Pro, GPT-5.6 Sol). Start with the free tier to test compatibility with your preferred model.\n\n> [!TIP]\n> **Save money getting started** *(updated Jul 2026)*. Google still offers a [1-month free trial on AI Pro](https://one.google.com/ai) for new subscribers, and AI Pro family sharing lets one subscriber extend AI benefits to up to 5 family members at no extra cost. Ultra pricing improved in May 2026: the top tier dropped from $249.99 to **$200/mo**, and a new **$100/mo Ultra tier** was added for lighter-but-regular development loads. Antigravity quotas were also raised roughly **9x** from their April 2026 low point, so the old weekly-cap anxiety is mostly obsolete — though weekly limits still exist for sustained heavy use, and how Antigravity quota interacts with family sharing is not clearly documented (coordinate if mul","github_created_at":"2025-12-18T19:47:38+00:00","created_at":"2026-07-11T11:35:17.123829+00:00","updated_at":"2026-09-20T06:24:05.785487+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"framework","name":"framework"},{"slug":"google-antigravity","name":"google-antigravity"},{"slug":"knowledge-management","name":"knowledge-management"},{"slug":"llm","name":"llm"},{"slug":"prompt-engineering","name":"prompt-engineering"},{"slug":"rag","name":"rag"}],"trust":{"provenance":{"is_fork":false,"github_id":1119131583,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:24:03.499Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":5,"days_since_push":0,"last_release_at":"2026-08-27T16:13:10Z","stars_delta_30d":46,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:35:18.607Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:24:04.585Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T06:24:04.585Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T06:24:04.585Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:24:04.585Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need persistent memory and structured reasoning capabilities that enhance any LLM used as an AI agent or assistant."],"when_not_to_use":["If your project requires a platform with extensive pre-built integrations beyond mere memory management for LLMs, Athena-Public may not offer sufficient out-of-the-box integration support."],"source":"enrich:decision_facts","observed_at":"2026-07-12T17:38:48.769Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Persistent memory & governed autonomy for AI Agents, built in Python."}]}}