AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
LLM Infra/
chidori
chidori logo

chidori

Active·★ 1.4k·Apache-2.0·Updated 2026-11-16

Chidori's premise is that agents are non-deterministic, expensive and long-running, which makes them hard to debug and fragile in production. Its answer is a single boundary: agents are written as plain async TypeScript, and every LLM call, tool call and HTTP request goes through the runtime as a recorded host call.

Because the runtime sees every side effect, a run can be checkpointed at each safepoint and resumed in a new process after a crash, replayed byte-identically with zero LLM calls for debugging, or suspended to disk by chidori.input() or a named signal until a human answers, minutes or days later. A recorded run can be committed to Git as an integration test that costs nothing to run. Determinism is enforced with a fixed clock and seeded randomness.

It ships as one Rust binary with an embedded pure-Rust JavaScript engine, so there is no Node, Deno or V8 to install, and TypeScript and Python SDKs talk to it over HTTP. The trade-off is a new runtime with its own constraints: agent code has to go through chidori.* calls to get these guarantees.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-06.

License
Apache-2.0
Latest release
v3.8.1 · 2026-08-30
Last commit
2026-11-06
Contributors
4
Forks
62
Open issues and PRs
16
First published
2023-07-19
npm package
@1kbirds/chidori 3.8.1 · 28 downloads last week

Source: GitHub, npm and PyPI public APIs.

#durable-execution#agent-framework#typescript#rust#replay#checkpointing#human-in-the-loop
$ Install
$ curl -fsSL https://raw.githubusercontent.com/ThousandBirdsInc/chidori/main/scripts/install.sh | sh
↗ Visit site★ GitHub
01

Features

01Replay any recorded run byte-identically with zero LLM calls
02Checkpoints at every host safepoint, so a killed run resumes in a new process
03chidori.input() and named signals suspend a run to disk while waiting for humans
04Commit a recorded run as a zero-cost integration test
05One self-contained Rust binary: no Node, Deno or V8 required
02

Why choose it

+Replay any run with zero LLM calls and identical output, which makes non-deterministic bugs reproducible.
+Runs survive crashes and can wait days for human approval without keeping a process alive.
+Recorded runs double as zero-cost regression tests in CI.
03

Trade-offs

!Agents must be written against Chidori's runtime and its chidori.* calls, which is a lock-in compared with plain SDKs.
!An embedded JavaScript engine, not Node, so some npm packages and Node APIs may not be available.
!A smaller ecosystem than mainstream agent frameworks.
04

Maintenance check

ActiveChecked: 2026-11-10
Last commit
2026-10-22
Commits, last 90 days
16
Releases, last 90 days
1
Latest release
v3.8.1 (2026-08-30)
Open issues
16
Recent issues with at least one comment
0/3
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 6, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #195 User memory as a replay-safe Chidori host call0 comments · 2026-09-29
  • #192 Consider rusty_alloc in place of mimalloc0 comments · 2026-09-04
  • #182 Fleet-mode resume of a paused session fails with `reading resume source ./__no_default_agent__.ts` when the persisted run state cannot be se0 comments · 2026-08-22
  • #38 🌟 Chidori x WisePick - Replayable Routing & Deterministic Agent Semantics0 comments · 2026-05-25

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

TypeScript
Agent language + SDK
Verified via docs
Python
SDK
Verified via docs
macOS / Linux
Binary
Verified via docs
06

Quick start

1
$ curl -fsSL https://raw.githubusercontent.com/ThousandBirdsInc/chidori/main/scripts/install.sh | sh
07

Use cases

↳Debugging non-deterministic agent bugs by replaying the exact run
↳Long-running agents with approval steps that may wait for days
↳Regression-testing agent behavior in CI without paying for tokens
08

Alternatives

⚡Top VS:
VSboxlite★2.7k→VSAReaL★5.9k→VSyomo★1.9k→VSagent-landing-zone★1.2k→
boxlite logo
boxlite★ 2.7k
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
VSCompare→
AReaL logo
AReaL★ 5.9k
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
VSCompare→
yomo logo
yomo★ 1.9k
🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.
VSCompare→
llama-cpp-agent logo
llama-cpp-agent★ 663
The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.
agent-landing-zone logo
agent-landing-zone★ 1.2k
Enterprise-grade landing zone for AI agent applications on Azure. Deploy the secure infrastructure, the agent app, or both — built on Microsoft Foundry and Microsoft Agent Framework, with Zero-Trust networking, observability and IaC.
VSCompare→
Proxima logo
Proxima★ 1.2k
Multi-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API
open-multi-agent logo
open-multi-agent★ 7.1k
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
VSCompare→
os-moda logo
os-moda★ 122
Your server fixes itself at 3am. You sleep. AI-native operating system built on NixOS.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
ThousandBirdsInc /
chidori
↗

An agent runtime that records every side effect, so runs replay for free, survive crashes and pause for humans

1.4k62Apache-2.0
Last commit6d ago
StatusActive
CategoryLLM Infra
Contributors4
Latest releasev3.8.1
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
© 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.