CONTINUUM
Active·★ 24·Apache-2.0·Updated 2026-10-24
CONTINUUM provides verifiable semantic recovery for long-running AI agents, preventing work duplication and token waste during crashes. It achieves this through compact semantic checkpoints, independent environment revalidation, and a provenance-aware state tracking system.
#Semantic Checkpoints#Agent Recovery#Idempotent Actions#Environment Revalidation#Tamper-Evident Log#LLM Agents#Fault Tolerance
01
Features
01Semantic checkpoints: Compact, versioned, inspectable state, not a transcript dump.
02Idempotent action ledger: Refuses duplicate external side effects; surfaces uncertain ones for reconciliation.
03Environment revalidation: Every checkpoint component verified against the current world before resume.
04Tamper-evident log: Hash-chained event log (36 event types) with integrity verification.
05Recovery engine: Seven recovery modes with a deterministic, sealed next-action contract.
02
Compatibility
Python
Runtime
Verified via docs
Docker
Container
Verified via docs
LangGraph
Framework
Verified via docs
LangChain
Framework
Verified via docs
OpenAI Agents SDK
Framework
Verified via docs
SQLite
Database
Verified via docs
03
Quick start
1
$ git clone https://github.com/Cyrax321/CONTINUUM.git
2
$ cd CONTINUUM
3
$ pip install -e ".[dev]"
04
Use cases
↳Resuming long-running AI agent tasks after crashes without replaying work, saving tokens and preserving decisions.
↳Wiring a coding agent (e.g., Claude Code, Gemini CLI) to capture file writes as hash-chained evidence and refuse duplicate side effects.
↳Integrating with various LLM frameworks (LangChain, LangGraph, OpenAI Agents SDK) to add robust persistence and verifiable recovery capabilities.
↳Ensuring the integrity and provenance of agent actions and state through a tamper-evident event log.
05
Alternatives
kaeru★ 48
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
hera★ 946
Hera makes Python code easy to orchestrate on Argo Workflows through native Python integrations. It lets you construct and submit your Workflows entirely in Python. ⭐️ Remember to star!
okf-agent-memory★ 836
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
projectmem★ 866
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
telemem★ 494
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
aoci-code★ 1.7k
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.
Comments
Log in to leave a comment
No comments yet. Be the first!