PyPI · npm62Moderatehealth index

nseney1/Soma-GovernanceSoma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.
Python★ 2↓ 3,035/moOct 6, 2026
Go · PyPI60Moderatehealth index

Clawdlinux/agent-native-formatToken-minimal system views for AI agents. Translate Kubernetes and live state into compact Agent Native Format with Go tooling and governed execution primitives.
Go · Python★ 1Sep 13, 2026
npm60Moderatehealth index

TaewoooPark/Agent-BlackboxLocal-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
TypeScript★ 74↓ 130/moSep 12, 2026

blackwell-systems/gcf-goGCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Go★ 7Oct 20, 2026
npm60Moderatehealth index

wundercorp/openmodelUse any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.
TypeScript · JavaScript · CSS★ 18↓ 570/moSep 17, 2026
npm59Moderatehealth index
Python · Shell · JavaScript★ 1↓ 1,987/moSep 11, 2026
Packagist · npm59Moderatehealth index
PHP★ 146↓ 9,391/moSep 13, 2026
PyPI59Moderatehealth index

wesleysimplicio/simplicio-loop🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.
Python★ 2↓ 1,375/moSep 15, 2026
PyPI57Moderatehealth index

blackwell-systems/gcf-pythonGCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Python★ 5↓ 11.4K/moOct 3, 2026
npm57Moderatehealth index

psjostrom/frontloadLocal-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.
TypeScript★ 0↓ 42/moSep 13, 2026
npm · Go · PyPI56Moderatehealth index

firstops-dev/whittleCarves your agent's tool outputs down to what matters. Never cuts what doesn't come back.
Go · Python★ 60↓ 18/moOct 21, 2026
npm56Moderatehealth index
TypeScript★ 12↓ 308/moSep 13, 2026
npm51Moderatehealth index

MelnixDev/context-goblinAn OpenCode plugin that hoards tiny project-context notes so agents read less and waste fewer tokens.
TypeScript · Shell · JavaScript★ 1↓ 766/moSep 9, 2026
npm51Moderatehealth index

blackwell-systems/gcf-typescriptGCF TypeScript implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
TypeScript★ 4↓ 187.4K/moSep 18, 2026
npm51Moderatehealth index

rootstudioyaml/claude-token-saverRoute the easy work your expensive Claude model keeps repeating down to haiku/sonnet — post-hoc session analysis, no realtime router, no extra LLM calls.
JavaScript★ 1↓ 7,768/moSep 9, 2026
PyPI · Go50Moderatehealth index

blackwell-systems/gcf-proxyMCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.
Go★ 11↓ 248/moOct 20, 2026
npm50Moderatehealth index
TypeScript · JavaScript★ 2↓ 2,563/moSep 18, 2026

ralphmoran/ticket-lensPrivacy-first CLI that transforms Jira tickets into AI-ready briefs. 60–80% fewer tokens. No relay. Pipe-friendly.
JavaScript★ 3↓ 5,462/moSep 10, 2026

codefly-dev/gortkGo-native, zero-dependency LLM command-output compressor — an embeddable take on rtk (the Rust 'token killer') with lossless-by-default compression and credential redaction.
Go★ 0Sep 11, 2026
HTML★ 4Sep 8, 2026
Go · crates.io · npm42Weakhealth index

itaides/leanpromptZero-dependency prompt compression for LLM applications. One deterministic algorithm, three native SDKs (TypeScript/Bun, Rust, Go) with byte-identical output. No ML model, no downloads.
TypeScript · Rust · Go★ 0Sep 24, 2026
Go · npm · PyPI42Weakhealth index

khanglvm/agentfmtAdaptive JSON-to-agent terminal output with exact token-aware format selection
Go★ 0Sep 13, 2026

evan-choi/pxpipe-goGo port of pxpipe core - cut Claude Code token usage by rendering text context as images
Go★ 7Oct 19, 2026
Go★ 0Sep 10, 2026

neural-llm-io/power-claudeLocal orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.
Python · HTML · JavaScript★ 5Sep 5, 2026
sukirman1901/make-latenUniversal efficiency toolkit for AI coding agents — compress, cache, route, learn and optimize token usage
TypeScript · HTML · JavaScript★ 1↓ 3,303/moAug 2, 2026
JavaScript · Python★ 20↓ 3,973/moOct 11, 2026

Sjstar007/oh-my-orqoh-my-orq — Autonomous multi-agent orchestration framework to generate apps from scratch using 30 specialized AI agents. Includes persistent shared memory, auto-codebase learning, 14 token optimization strategies (saving up to 70%), MCP integration, Hermes notifications, visual themes, and a live token usage dashboard.
JavaScript · HTML★ 1↓ 73/moSep 17, 2026

bassprofressor-lab/openwolf-enhancedEnhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.
TypeScript · JavaScript★ 6↓ 2,762/moSep 14, 2026