Havuz

LeanCTX, coding agent’lara yerel bir katman üzerinden görevle ilgili context’i seçip sıkıştırarak ileten ve kullanım maliyetini izleyen bir yazılımdır.

Neden yükseliyor · 188 günde 3.839 yıldıza ve son 28 günde 292 commit’e ulaşması dikkat çekiyor. README’de çok sayıda coding agent desteği, tek komutla kurulum ve ölçülebilir token tasarrufu öne çıkarılıyor; ancak bu tasarruf iddiası kullanım senaryosuna bağlı ve bağımsız doğrulama bilgisi verilen metinde yok. Commit etkinliği yüksek olsa da 5 farklı yazar katkının sınırlı sayıda kişide yoğunlaşabileceğini gösteriyor.

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

AgentSafe, agent veya API isteklerini hedefe iletmeden önce yetkilendirme kontrolünden geçiren bir HTTP execution gateway’idir.

Neden yükseliyor · 45 günlük yaşına karşılık 589 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak commit’lerin yalnızca 3 farklı yazardan gelmesi, aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor. Yıldızların nedeni verilerden kesin olarak çıkarılamaz.

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayab

Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the

PeerBridge MCP, farklı coding agent'ları yerel bir çalışma alanında yönetip görev, izin ve kanıt kayıtlarını ortak bir kontrol odasında birleştirir.

Neden yükseliyor · 41 günde 239 yıldıza ulaşmış; ancak bunun nedenini gösteren veri yok. README'deki çoklu agent yönetimi ve audit/evidence yaklaşımı ilgi çekici olsa da son 28 günde 4 commit ve 1 farklı yazar, sürdürülen geliştirme ve bağımsız katkı hakkında sınırlı kanıt sunuyor.

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agent

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable

Lossless, local, provable memory for AI agents: every Claude Code session kept on your own computer, word for word, compressed and sealed, a

Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.

让 Agent 通过对话直接操作你的商城、SaaS、CRM 或 ERP 后台，同时保留原有权限、审批与审计。Self-hosted hub for agents operating existing business systems safely.

Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in.

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support E

CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs

A swarm of forensic agents, on your machine, on the record. Open-source agentic digital forensics and incident response under the AGPL: agen

State-Aware Collaboration Protocol: auditable work receipts for AI agents.

Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

Laravel audit log & change history with real actor attribution (user / job / command / scheduler), cross-model change traces, time machine,

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew

Transparent randomization tools with fairness receipts, replayable draws, giveaways, tournaments, and live rooms.

AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts any

A verifiable semantic kernel for legacy business systems: build a governed domain ontology from your existing schema, and make every verdict

Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfa

Cryptographic trust and authorization evidence for AI agents. Every action a receipt, every grant a proof.

Evidence-gated local workflow clock: loops repeat work, the clock advances trust.

Local Codex control with bounded runs, crash recovery, and auditable results. Optional ChatGPT bridge.

Open-source governance infrastructure for AI-assisted legal work

Enterprise reporting system with multi-currency Decimal precision (<50ms), signed 3-stage approval workflow, real-time dashboard, tax/bank i

a DSL for automated deterministic rules. Built for AI agents and quantitative Trading systems.

Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.

Stock investment and portfolio decision workflows for AI agents: Claude Code, Codex, OpenClaw, DeepSeek Harness (dsh plugin) or your own scr

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.

Local-first AI workspace for law firms: case files stay on your machine, local or chosen cloud model, hash-chained audit trail with its own