AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Security & Safety/
tardygrada
tardygrada logo

tardygrada

Active·★ 23·MIT·Updated 2026-08-11

Tardygrada is a programming language that compiles to MCP servers, where every value carries cryptographic proof of its creator, creation time, and integrity. It guarantees integrity via mprotect, SHA-256, ed25519, and BFT consensus (proven in Coq), provenance with signed metadata, and a full audit trail. However, it does not guarantee truth; it only ensures the value has not been changed, providing 100% proof even after 100 handoffs among agents.

#agent-framework#ai-agents#ai-safety#byzantine-fault-tolerance#c#coq
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#cryptography
#ed25519
$ Install
$ git clone https://github.com/fabio-rovai/tardygrada && cd tardygrada && make
↗ Visit site★ GitHub
01

Features

01Integrity guarantees via OS kernel (mprotect) and cryptography (SHA-256, ed25519)
02Provenance tracking with signed metadata (who, when)
03Full audit trail for every operation
04Multiple immutability tiers (let, @verified, @hardened, @sovereign)
05Compiles to MCP servers for integration with agent frameworks
02

Compatibility

Linux
Linux (native)
Verified via docs
03

Quick start

1
$ git clone https://github.com/fabio-rovai/tardygrada
2
$ cd tardygrada
3
$ make
04

Use cases

↳Securing multi-agent systems where integrity of data passed between agents is critical
↳High-confidence domains like medical diagnosis requiring tamper-proof evidence
↳Retrofitting existing agent frameworks (CrewAI, LlamaIndex, MiroFish) with integrity proofs
05

Alternatives

⚡Top VS:
VSIntercept★32→VSattestix★846→VSantrieb-mcp-server★14→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
nobulex
★40
→
Intercept logo
Intercept★ 32
The enforcement layer for AI agents. Intercept enforces hard, deterministic limits on what agents can do at the MCP transport layer — before execution.
VSCompare→
attestix logo
attestix★ 846
Attestix - Attestation Infrastructure for AI Agents. DID-based agent identity, W3C Verifiable Credentials, EU AI Act compliance layer, delegation chains, and reputation scoring. 47 MCP tools across 9 modules.
VSCompare→
antrieb-mcp-server logo
antrieb-mcp-server★ 14
MCP server that validates AI-generated infra code on real VMs and self-corrects until it works.
VSCompare→
nobulex logo
nobulex★ 40
The trust economy for autonomous AI agents. Credit scores for machines. Agents earn Trust Capital through verified behavior, gating what they are allowed to do. Autonomy earned, not granted.
VSCompare→
ThumbGate logo
ThumbGate★ 29
Pre-action gates for AI coding agents. Skill disclosure cuts tokens. Hallucination and PII checks harden outputs. 👍 Thumbs up reinforces good behavior. 👎 Thumbs down blocks repeated mistakes. Free is local. History-aware lessons distill vague feedback. Team adds shared lessons and org visibility, plus generated review views.
VSCompare→
SchemaPin logo
SchemaPin★ 16
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
VSCompare→
agent-bom logo
agent-bom★ 35
Open security scanner for AI supply chain: agents, MCP, containers, cloud, GPU, and runtime with blast-radius analysis.
VSCompare→
cordum logo
cordum★ 511
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
VSCompare→
See all alternatives →
fabio-rovai /
tardygrada
↗

Trust infrastructure for AI agents. Know who produced a value, when, and that it hasn't been tampered with. Zero dependencies. Pure C.

23MIT
Last commit2mo ago
StatusActive
CategorySecurity & Safety
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit