repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 18h ago
prasenjeet-symon/ogcode
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%SentryCode: Real-time Auditor + Honeytokens for AI Coding Agents [P] →
- PossiblePossibly related (embedding) · 53%TraceLab: Characterizing Coding Agent Workloads for LLM Serving →
- PossiblePossibly related (embedding) · 50%Ornith-1.0: self-improving open-source models for agentic coding →
- PossiblePossibly related (embedding) · 47%Gigatoken: A new open source tokenizer ~100x faster than Tiktoken, -500-1000x faster than Huggingface →
- PossiblePossibly related (embedding) · 52%GigaToken: ~1000x faster Language model tokenization →
- PossiblePossibly related (embedding) · 51%Code mode yields a 99.2% cost reduction in our systems →
Covers
Implements
Covers (incoming)
Related across the graph
paperTraceLab: Characterizing Coding Agent Workloads for LLM ServingnewsOrnith-1.0: self-improving open-source models for agentic codingnewsSentryCode: Real-time Auditor + Honeytokens for AI Coding Agents [P]newsGigaToken: ~1000x faster Language model tokenizationnewsCode mode yields a 99.2% cost reduction in our systemsnewsGigatoken: A new open source tokenizer ~100x faster than Tiktoken, -500-1000x faster than Huggingface