|
TulaDB — Financial state that stays balanced
TulaDB is a ledger-first database engine for value-exchange systems. It keeps balances, holds, reversals, and rejected transactions correct, durable, and rec...
|
76 % |
|
PtcRunner
PtcRunner is a runtime for building self-improving agents: the agent loop is a replaceable library, not the runtime, so you can change what an agent does wit...
|
76 % |
|
Vectorbea - Durable Agentic AI Workflows
Build and run durable, long-running AI agent workflows — with checkpoints, automatic retries, human approvals, live observability and resume-from-failure rec...
|
75 % |
|
WRTHOG — Personal AI, persistent execution.
A product and research blueprint for a persistent personal AI: source-linked memory, computer use, reusable skills, compute architecture, and measurable deve...
|
75 % |
|
Povenos | Execution Reality Testing
Prove that technical knowledge converts into correct action under pressure. Run real operational scenarios, watch decisions unfold, and see exactly where exe...
|
75 % |
|
Povenos | Execution Reality Testing
Prove that technical knowledge converts into correct action under pressure. Run real operational scenarios, watch decisions unfold, and see exactly where exe...
|
75 % |
|
TrigRun | Cron Infrastructure for Scheduled Webhooks and Scripts
Run scheduled webhooks, workflows, and scripts with execution history, retries, secrets, replay, backfill, and agent-ready API surfaces.
|
75 % |
|
Morphora — From issue to implementation
AI-assisted engineering execution platform. Transform bugs, incidents, feature requests, and technical work into verified code changes and review-ready pull...
|
75 % |
|
Zart — Workflows that survive failure
Durable execution for Rust. Write workflows that automatically persist every step to a database, survive process restarts, and never re-run completed work.
|
75 % |
|
Memomee — The memory control plane for AI agents
The memory governance and retrieval control plane for long-running AI agents. Recall broadly, govern rigorously, inject precisely — task state, decisions, an...
|
75 % |
|
Restore Gap — prove your recovery works
Run a real restore drill. Keep fresh recovery evidence. Refuse a guarded change until that evidence exists. Restore Gap is a free, offline, open-source recov...
|
75 % |
|
TraceBreak - Replay debugger for agent runs
TraceBreak records agent runs as linked event traces so teams can inspect, replay, and compare exactly where behavior changed.
|
75 % |
|
Ontral — Replay and Debug Production AI Agents
Ontral captures AI-agent executions into deterministic capsules so teams can replay failures, find the first divergence, test counterfactuals, prevent regres...
|
75 % |
|
Relai - AI Agent Regression Infrastructure
Relai captures agent failures as replayable test cases. Every production bug becomes a replay environment that proposed fixes must pass before your PR opens.
|
75 % |
|
Dicast — AI Code Review With a Three-Model Jury
AI code review that posts only what survives cross-examination. Every finding is heard by three independent models; two votes to post, three to block the merge.
|
75 % |
|
WeaveFlow | Build inspectable agent workflows in Go
WeaveFlow is a graph runtime written in Go for building, executing, and inspecting LLM agent workflows.
|
75 % |
|
Tracefold — fork() a running agent. Replay it deterministically.
Tracefold is a fork-native microVM runtime for agent execution and RL rollouts. Snapshot, fork, branch, and deterministically replay a running execution.
|
75 % |
|
Dossier Secure Enterprise: Decisions you can prove
An evidence architecture for consequential decisions.
|
74 % |
|
Promtact - reproducible verification for distributed systems
Turn rare distributed-system failures into deterministic tests your team can replay locally, in CI and inside its own infrastructure.
|
74 % |
|
Faultmark
We find the logic and security bugs your scanners miss, verify every one against your source, and hand you a concrete fix. You only pay for the bugs you keep.
|
74 % |
Detected social media networks