cost-control repositories
Trending repositories tagged cost-control, ranked by trending score. Updated daily.
-
1
archid21/rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
GitHub · TypeScript · 46 stars · 13 forks · +5 stars in 24 hours · Trending score 0.91
-
2
gluztm/dsh-chief
把盯流程的活交给 AI,你只管拍板。AI 管 AI —— 它自己盯流程、自己调度子代理,跑崩了先拦住。 Hand the workflow-watching to AI. You only make the call - it minds the flow, keeps subagents on track, and stops a runaway before it reaches you.
GitHub · JavaScript · 10 stars · 0 forks · +2 stars in 24 hours · Trending score 0.60
-
3
beizhu-1209/AIHelms
企业级 AI 资源纳管平台,提供统一 AI网关、Token调度能力,纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型,并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表,帮助企业精准控制成本、量化 ROI,高效治理 AI 资产。
GitHub · Python · 1,035 stars · 106 forks · 0 stars in 24 hours · Trending score 0.59
-
4
caidaoli/ccLoad
Self-hosted AI API gateway for Claude Code, Codex and Gemini: pool API keys and subscription accounts behind one endpoint with failover, protocol conversion and cost tracking.
GitHub · Go · 443 stars · 78 forks · 0 stars in 24 hours · Trending score 0.50
-
5
anoop2811/software-factory-template
Open-source software factory for Codex, Claude Code and OpenCode: enforceable checks, independent reviews, budget controls, observability and bounded repair loops.
GitHub · Go · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.10
-
6
imrohitagrawal/quorum-ai
Multi-model LLM orchestration with cost approval, source-backed synthesis, disagreement, uncertainty, and degraded-mode disclosure.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10
-
7
theagentplane/tokenops
Run-aware token governance for multi-agent systems.
GitHub · Python · 84 stars · 23 forks · 0 stars in 24 hours · Trending score 0.08
-
8
VeridicalTech/Edward
The supervisor for coding agents that run when nobody's watching — deterministic guardrails + local semantic scorer + resumable interventions, every decision signed.
GitHub · Python · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.08
-
9
metahumansworld/SIwithin
Run an agent CLI unattended, on a brief, inside a fence, under a budget, with a ledger.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07
-
10
ENDEVSOLS/LongGuard
In-flight circuit breaker & loop recovery for LangGraph, LangChain, OpenAI & Anthropic agents. Catches reasoning loops, prevents runaway LLM costs with budget hard caps, and auto-injects Reflect & Pivot prompts.
GitHub · Python · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.07
-
11
project-koku/koku
An open source solution for cost management of cloud and hybrid cloud environments.
GitHub · Python · 317 stars · 129 forks · 0 stars in 24 hours · Trending score 0.05
-
12
vishal-dehurdle/state-harness
Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness
GitHub · Python · 18 stars · 2 forks · 0 stars in 24 hours · Trending score 0.04
-
13
robusta-dev/krr
Prometheus-based Kubernetes Resource Recommendations
GitHub · Python · 4,783 stars · 289 forks · 0 stars in 24 hours · Trending score 0.04
-
14
vijaym2k6/SteerPlane
The safety layer for the AGI era. Runtime guardrails for autonomous AI agents.
GitHub · Python · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
15
loopgain-ai/loopgain
An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of running to a fixed max_iterations cap. Real-time loop-gain (Aβ) bands + best-so-far rollback. Adapters for LangGraph, CrewAI, AutoGen, LangChain, OpenAI Agents, and Claude Agent SDK; raw API for custom stacks.
GitHub · Python · 127 stars · 11 forks · 0 stars in 24 hours · Trending score 0.00
-
16
voly-codes/voly
Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.
GitHub · Python · 17 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
17
Fame510/SHACKLE
SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy constraints in real time, with an audited decision engine, SP-1.0 protocol spec, Rust/TypeScript clients, and SOC2-aligned compliance tooling.
GitHub · Python · 18 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
18
Zoria-Lind/dsh-token-optimizer
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
GitHub · JavaScript · 20 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
19
alphaparkinc/genpark-agent-budget-rate-limit-throttle-skill
GenPark AI Agent Skill - Token bucket rate limiter and budget throttle engine protecting downstream APIs and managing agent session token costs.
GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
20
Alpha-Park/genpark-agent-budget-rate-limit-throttle-skill
GenPark AI Agent Skill - Token bucket rate limiter and budget throttle engine protecting downstream APIs and managing agent session token costs.
GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
21
SteelUnion/dsh-confirm-gate
DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.
GitHub · JavaScript · 101 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
22
mgkvibez/agentic-harness-orchestrator
Route each sub-task to the model that suits it: from-scratch orchestrator with a blackboard, strict JSON contracts, cost and step ceilings, and an auditable trace.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00