amr/memex
1
0
Fork 0
Code Issues 12 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

chore: unify bold syntax to single asterisk in .org files and update legacy memex-amero references

Browse Source
This commit is contained in:
Amr Gharbeia
2026-04-01 12:37:45 -04:00
parent 78ba3112cb
commit d364f90ff6
102 changed files with 955 additions and 955 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
notes/token-optimization.org
View File

@@ -4,7 +4,7 @@
#+FILETAGS: :strategy:token:optimization:cost:psf:
* Overview
The **Token Optimization** project defines the strategy and implementation for cost-effective LLM usage. It implements a multi-tier, multi-provider approach to minimize inference costs while maximizing reasoning capability through smart routing and context compression.
The *Token Optimization* project defines the strategy and implementation for cost-effective LLM usage. It implements a multi-tier, multi-provider approach to minimize inference costs while maximizing reasoning capability through smart routing and context compression.
* Phase A: Demand (PRD)
:PROPERTIES:
@@ -15,10 +15,10 @@ The **Token Optimization** project defines the strategy and implementation for c
Minimize LLM operational expenses while maintaining high-fidelity agentic performance.
** 2. User Needs
- **Multi-Tier Strategy:** Resolve tasks using the cheapest model that meets the required intelligence threshold.
- **Failover Resilience:** Automated fallback chain (Gemini -> OpenRouter -> GPT-4o).
- **Context Efficiency:** Implement pruning and RAG to avoid token bloat.
- **Usage Transparency:** Real-time tracking and budget alerts.
- *Multi-Tier Strategy:* Resolve tasks using the cheapest model that meets the required intelligence threshold.
- *Failover Resilience:* Automated fallback chain (Gemini -> OpenRouter -> GPT-4o).
- *Context Efficiency:* Implement pruning and RAG to avoid token bloat.
- *Usage Transparency:* Real-time tracking and budget alerts.
** 3. Success Criteria
*** TODO 80% of queries handled by Tier 1 (Free/Fast) models