AgentLedger alternatives

1

BackBond Agent Scan

by BackBond

A

Vet MCP tool manifests before attachment; returns block, review, or no blocking finding.

2

MCP

by decionis.com

A

Authorize consequential AI agent actions before execution

3

Projectmem

by riponcm

A

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

4

Kosha Model Discovery

by sriinnu

B

Tells your agent which model to use and what it costs, across 45 providers and local runtimes.

MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

6

Lockstep

by lockstep-team-agent

A

Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.

7

MCP Server

by pathmodeio

B

Deterministic intent preflight before your agent builds: six gates, keyless, no model call.

8

Aml

by oceanalt.com

A

Screen a payee address before an AI agent pays: sanctions, mixers, scam lists, on-chain risk.

9

Aletheia Runtime Safety & Scope Creep Filter

by vikasny30

B

Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

10

Particles

by linkedparticles.org

C

An append-only ledger of sourced, dated, confidence-scored claims your agent cites and you audit

11

Trazum

by Davmunrey

A

Trazum as an MCP server: let an agent price and budget its own prompts before it sends them.

12

lurq

by jadenryu

A

Verify npm packages before your AI agent installs them: hallucinations, advisories, API drift.

13

X402 Trust

by JonasFuchss

B

Trust & reliability data for x402 endpoints before your agent pays them.

14

Mnki

by MNKIAgentOS

B

MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

15

VERAX

by verax-ai

B

The body an agent asks before it acts: decide, approve, and keep a signed record on your machine.

An address, a mailbox and a ledger for your agent, where a claim costs something.

17

Pendpost

by pendpost

B

Local-first social MCP: an agent drafts and schedules posts; you approve before anything publishes.

18

Vox MCP

by linxule

B

Multi-model AI gateway — 8 providers plus local models, no system prompt injection.

19

Lovec

by lovec-tech

B

Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.