# loopx-project/loopx

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/loopx-project-loopx).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

6,560 stars · 614 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/loopx-project/loopx
- Homepage: https://loopx-project.github.io/loopx/
- awesome-repositories: https://awesome-repositories.com/repository/loopx-project-loopx.md

## Topics

`agent-control-plane` `agent-harness` `agentic-software` `ai-agents` `auto-research` `claude-code` `codex` `local-first` `long-horizon-agents` `multi-agent` `rsi`

## Description

LoopX is a local-first control plane for long-running coding agents. It keeps goals, todos, claims, gates, quota and evidence in durable state outside any chat session, so work carries on across restarts, changes of owner and swaps of agent runtime. Agents are woken on a recurring heartbeat, and each turn is gated by quota and authority before one bounded segment of work runs. A completion claim is accepted only after an independent validator checks the real outcome.

What sets it apart is how it handles trust and ownership. An agent's own "done" is treated as unverified evidence, and results are committed only after validation, with receipts that let a crashed turn resume from the first uncommitted step. Peer agents share one goal through claims, time-limited leases and explicit handoffs, and stale executors are fenced out. Stalled routes trigger replanning obligations. It connects to several agent hosts, including Codex, Claude Code and Kiro CLI, as well as custom runners and generic CLI adapters, and keeps one shared goal lifecycle across them.

Around that core sits a human review layer: a local dashboard and chat workspace where people see agent lanes, review output as scoreable cards, give feedback, and answer scoped decision gates. Status views and kanban boards are read-only projections of canonical state. Optional capabilities cover issue-to-pull-request workflows, change-quality review receipts, scheduled reports, research exploration with evidence graphs, and mirroring to boards and chat channels such as Lark. Providers and extensions plug in around the kernel without taking over its authority.

LoopX is written in Python and installs as a command-line tool, with install, health-check and upgrade commands, slash-command skills for supported hosts, and an optional desktop app.

## Tags

### Artificial Intelligence & ML

- [Agent Safety and Verified Completion](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-safety-and-verified-completion.md) — Treats an agent's self-reported completion as unverified evidence that the control plane must verify and settle before work counts as finished. ([source](https://loopx-project.github.io/loopx/benchmarks/swe-marathon/))
- [Peer Claim and Lease Authority](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-team-coordination-patterns/peer-claim-and-lease-authority.md) — Separates claims, time-bounded leases and lifecycle authority among peer agents so handoffs never imply completion rights. ([source](https://loopx-project.github.io/loopx/blog/from-one-shot-agents-to-long-horizon-control/))
- [Cross-Session Goal Continuity](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-task-execution/long-horizon-workflows/cross-session-goal-continuity.md) — Keeps goals, todos, dependencies, acceptance criteria and recovery points in durable local state so work survives across sessions and agent hosts. ([source](https://github.com/loopx-project/loopx/blob/main/AGENTS.md))
- [Cross-Host Goal Continuity](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-host-goal-continuity.md) — Connects Codex, Claude Code and other runtimes to one shared goal state so work moves between hosts without losing evidence. ([source](https://github.com/loopx-project/loopx#readme))
- [Goal and Todo Tracking for Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/goal-and-todo-tracking-for-agents.md) — Stores goals, todos, claims, evidence, handoffs and gate decisions in durable local state so work carries over across sessions, hosts and providers. ([source](https://loopx-project.github.io/loopx/))
- [Host-Driven Goal Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/host-driven-goal-loops.md) — Turns an external agent session into a governed goal loop where each approved tick runs one bounded segment and returns one typed result. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/dsh_goal_mode/README.md))
- [Command-Based Outcome Validation](https://awesome-repositories.com/f/artificial-intelligence-ml/independent-agent-validators/command-based-outcome-validation.md) — Runs a user-supplied command to check the real outcome and blocks commit or quota spend when validation fails. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/runtimes/codex-cli/loopx-turn-codex-cli-quickstart.md))
- [Peer Ownership Leases](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-coordination/peer-ownership-leases.md) — Lets peer agents share a goal through claims, time-limited leases and handoffs, with epoch fencing so stale executors cannot overwrite current owners.
- [Control Planes Above Execution Hosts](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-agent-hosting/control-planes-above-execution-hosts.md) — Provides a durable control plane for goals, tasks, replanning, evidence, quotas and continuation above the host that runs agent work. ([source](https://github.com/loopx-project/loopx/blob/main/docs/showcases/cases/dsh-loopx-replan-demo.md))
- [Premature Completion Rejection](https://awesome-repositories.com/f/artificial-intelligence-ml/premature-completion-rejection.md) — Treats an agent's self-reported done as unverified evidence, so work continues until independent verification passes. ([source](https://loopx-project.github.io/loopx/benchmarks/swe-marathon/))
- [Project-Owned Agent Control Planes](https://awesome-repositories.com/f/artificial-intelligence-ml/project-owned-agent-control-planes.md) — Keeps goal, work queue, authority, evidence and recovery conditions in a project-owned control plane so agent work survives sessions, owners and external waits. ([source](https://loopx-project.github.io/loopx/docs/))
- [Native Goal Lifecycles](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-goal-definitions/native-goal-lifecycles.md) — Claims a bounded task from the work queue and drives an agent runtime through a strict goal-and-verify lifecycle with verified writeback of results and quota. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/kunluncode_goal_mode/README.md))
- [Verified Single-Turn Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-iteration-runs/verified-single-turn-execution.md) — Runs one bounded coding task through an agent CLI, then has an independent validator check the postcondition before commit and a single spend. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/runtimes/codex-cli/loopx-turn-codex-cli-quickstart.md))
- [Agent Run Resumption](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-run-resumption.md) — Keeps a local journal of binding identity, native ids and writeback receipts so a rerun resumes the same thread without repeating completed steps. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/kunluncode_goal_mode/README.md))
- [Agent Task Ownership Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-task-ownership-transfers.md) — Moves task ownership to another agent using handoff notes and typed transfer grants, keeping consultation and delegation separate from ownership adoption. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/capable-manager-semantic-handoff-v0.md))
- [Agent Todo Claims and Handoffs](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-todo-claims-and-handoffs.md) — Lets registered peer agents claim individual todos, work within declared write scopes and write back evidence, with any temporary coordinator holding no standing authority. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture.md))
- [Agent Value Scoring](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-value-scoring.md) — Rates agent value by combining output quantity, review-based quality, token cost and user attention cost into reviewable ratings. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/vision.md))
- [Agent Wake Cadence Scheduling](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-wake-cadence-scheduling.md) — Manages wake cadence, due times and backoff, and confirms the host applied the proposed timer before re-reading state on each heartbeat. ([source](https://github.com/loopx-project/loopx/blob/main/docs/development/control-plane-course/00-concept-primer.md))
- [Agent Work Review Feeds](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-work-review-feeds.md) — Presents agent output as ranked scoreable cards with evidence, cost and next step, surfacing gates and evidence gaps before routine activity. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/vision.md))
- [Semantic Context Handoffs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-task-orchestrators/task-hand-off-transfers/semantic-context-handoffs.md) — Passes work to another agent with purpose, decisions, constraints, evidence, commitments and expected return so the receiver continues instead of restarting. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/capable-manager-semantic-handoff-v0.md))
- [Continuation Controls](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-security-and-governance/agent-governance/continuation-controls.md) — Decides when authorized agent work may continue by applying heartbeat checks, scheduling, quota limits and explicit stop or wait conditions. ([source](https://github.com/loopx-project/loopx/blob/main/AGENTS.md))
- [Cross-Runtime Agent Runs](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-runtime-agent-runs.md) — Keeps goals, constraints and acceptance evidence consistent while models and execution runtimes change between runs. ([source](https://loopx-project.github.io/loopx/docs/))
- [Cross-Runtime Work Handoff](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-runtime-work-handoff.md) — Carries goal state and evidence between agent sessions on different hosts so work continues without losing context or ownership. ([source](https://github.com/loopx-project/loopx/blob/main/README.zh-CN.md))
- [Custom Runner Control Ticks](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-runner-control-ticks.md) — Exposes a small tick of commands that lets any shell or scheduler check whether to run, claim work, record progress and account for verified slices. ([source](https://github.com/loopx-project/loopx/blob/main/README.zh-CN.md))
- [Drift-Triggered Replanning](https://awesome-repositories.com/f/artificial-intelligence-ml/drift-triggered-replanning.md) — Raises a mandatory replan obligation after repeated consecutive drift receipts, forcing stalled agents to change course. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/capabilities/progress_review/README.md))
- [Evidence-Tracked Agent Work](https://awesome-repositories.com/f/artificial-intelligence-ml/durable-ai-agent-orchestration/evidence-tracked-agent-work.md) — Tracks long-running agent tasks together with the evidence they produce so progress persists across sessions and runtimes and can be verified. ([source](https://github.com/loopx-project/loopx/blob/main/CONTEXT.md))
- [Goal and Task Workspaces](https://awesome-repositories.com/f/artificial-intelligence-ml/goal-and-task-workspaces.md) — Presents goal direction, acceptance conditions, the work map and owner decisions in one workspace view, keeping task progress separate from goal acceptance. ([source](https://loopx-project.github.io/loopx/blog/semantic-software-development/))
- [Heartbeat Prompt Loaders](https://awesome-repositories.com/f/artificial-intelligence-ml/heartbeat-prompt-loaders.md) — Generates a short visible goal line plus a bootstrap loader that binds a goal and agent and fetches the current execution contract on every wake. ([source](https://github.com/loopx-project/loopx/blob/main/docs/heartbeat-automation-prompt.md))
- [Scoped Decision Gates](https://awesome-repositories.com/f/artificial-intelligence-ml/human-approval-gates/scoped-decision-gates.md) — Blocks only the lanes, tasks or decisions awaiting approval while independent eligible work keeps running. ([source](https://loopx-project.github.io/loopx/blog/agent-facing-kanban/))
- [Concrete Gate Questions](https://awesome-repositories.com/f/artificial-intelligence-ml/human-approval-gates/scoped-decision-gates/concrete-gate-questions.md) — Marks tasks needing a human decision as user-gate cards with a concrete question so agents stop and wait instead of guessing. ([source](https://github.com/loopx-project/loopx/blob/main/docs/integrations/lark-kanban-control-plane-adapter.md))
- [Run Reward Overlays](https://awesome-repositories.com/f/artificial-intelligence-ml/human-feedback-collection/run-reward-overlays.md) — Appends operator judgments, reasons and correction lessons to exact runs as overlays that later surface in status and warn on contradicting actions. ([source](https://github.com/loopx-project/loopx/blob/main/docs/state-interaction-model.md))
- [Journal-Based Turn Recovery](https://awesome-repositories.com/f/artificial-intelligence-ml/journal-based-turn-recovery.md) — Resumes interrupted agent turns by loading the original journaled plan and receipts so recovery restarts from the first uncommitted step. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/typescript-control-plane-migration-v0.md))
- [Long-Run Goal Alignment](https://awesome-repositories.com/f/artificial-intelligence-ml/long-run-goal-alignment.md) — Preserves original intent and stable acceptance criteria across replanning and handoff so long agent runs stay aligned with their declared goal. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/loopx-overall-roadmap-v0.md))
- [Peer Agent Task Coordination](https://awesome-repositories.com/f/artificial-intelligence-ml/peer-agent-task-coordination.md) — Coordinates tasks across peer agents and passes work between them while the control plane remains the single source of truth. ([source](https://github.com/loopx-project/loopx/blob/main/docs/integrations/README.md))
- [Per-Turn Decision Packets](https://awesome-repositories.com/f/artificial-intelligence-ml/per-turn-decision-packets.md) — Projects canonical state into a compact versioned packet of identity, allowed actions, gates and writeback commands, regenerated each turn instead of replaying history. ([source](https://github.com/loopx-project/loopx/blob/main/docs/development/control-plane-course/00-concept-primer.md))
- [Planned Long-Running Agent Work](https://awesome-repositories.com/f/artificial-intelligence-ml/planned-long-running-agent-work.md) — Takes a concrete goal, plans first, writes ordered todos, and advances one bounded, validated slice at a time toward the result. ([source](https://github.com/loopx-project/loopx/blob/main/docs/guides/newcomer-command-path.md))
- [Provider-Neutral Goal Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-neutral-goal-stores.md) — Keeps goal authority behind interchangeable file, SQLite or PostgreSQL stores so run history, status, quota and scheduling stay consistent across machines. ([source](https://github.com/loopx-project/loopx/blob/main/docs/project/technical-directions.md))
- [Replan Obligation Discharge](https://awesome-repositories.com/f/artificial-intelligence-ml/replan-obligation-discharge.md) — Clears a replan obligation only when the next state refresh carries new evidence, a hypothesis, a concrete blocker, or an evidence-linked vision path. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/capabilities/progress_review/README.md))
- [Safe Long-Running Todo Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/safe-long-running-todo-execution.md) — Drives long-horizon work as compact transitions: check the guard, pick one lane, validate, write durable state, spend once and refresh status. ([source](https://github.com/loopx-project/loopx/blob/main/docs/state-interaction-model.md))
- [Append-Only Event Ledgers](https://awesome-repositories.com/f/artificial-intelligence-ml/search-state-ledgers/append-only-event-ledgers.md) — Records accounting, decision, evidence and work events in an append-only ledger so status is a replayable projection and past decisions stay auditable.
- [Shared Todo Ownership Contracts](https://awesome-repositories.com/f/artificial-intelligence-ml/shared-todo-ownership-contracts.md) — Defines a shared todo contract covering work items, owners, approval gates and how tasks continue between agent sessions. ([source](https://github.com/loopx-project/loopx/blob/main/docs/README.md))
- [Stalled Route Replanning](https://awesome-repositories.com/f/artificial-intelligence-ml/stalled-route-replanning.md) — Detects when the current approach can no longer satisfy the goal and triggers a new plan instead of repeating failing local attempts. ([source](https://github.com/loopx-project/loopx/blob/main/docs/showcases/cases/independent-cpp-accuracy-long-run.md))
- [Structured Human Feedback on Agent Work](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-human-feedback-on-agent-work.md) — Captures one-tap human judgments such as useful, wrong direction, or risky on agent output, turning periodic reviews into a continuous feedback signal. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/vision.md))
- [Transactional Turn Settlement](https://awesome-repositories.com/f/artificial-intelligence-ml/transactional-turn-settlement.md) — Validates the turn journal, authorizes external providers, checkpoints outcomes and reduces everything into one typed result so replays finish with a single call. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/typescript-control-plane-migration-v0.md))
- [Turn Outcome Signals](https://awesome-repositories.com/f/artificial-intelligence-ml/turn-outcome-signals.md) — Returns a compact typed turn result telling callers whether to commit, repair, replan, wait, or ask the user next. ([source](https://github.com/loopx-project/loopx/blob/main/docs/product/runtimes/codex-cli/loopx-turn-codex-cli-quickstart.md))
- [Typed Control-Plane Tool Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/typed-control-plane-tool-servers.md) — Registers a tool server in the host's settings so sessions can check quota, claim and complete tasks, and review results through typed calls. ([source](https://github.com/loopx-project/loopx/blob/main/loopx/kiro_cli_goal_mode/README.md))
- [Typed Worker Turn Exchange](https://awesome-repositories.com/f/artificial-intelligence-ml/typed-worker-turn-exchange.md) — Exchanges structured turn envelopes and results with external workers, adding preview, durable commit, replay and recovery for programmatic hosts. ([source](https://github.com/loopx-project/loopx/blob/main/docs/guides/minimal-custom-runtime-example.md))
- [Peer Agent Handoff Contracts](https://awesome-repositories.com/f/artificial-intelligence-ml/worker-agent-definitions/coordinator-worker-orchestration/peer-agent-handoff-contracts.md) — Lets manager-to-worker and worker-to-worker agents request help, exchange accepted artifacts, challenge dependencies and propose replanning through one shared contract. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture/rfcs/loopx-overall-roadmap-v0.md))

### DevOps & Infrastructure

- [Quota-Gated Agent Ticks](https://awesome-repositories.com/f/devops-infrastructure/recurring-job-scheduling/agent-run-scheduling/quota-gated-agent-ticks.md) — Wakes agents on a recurring heartbeat, gates each turn by quota and authority, runs one bounded segment, then validates, writes back and spends quota.
- [Recurring Wake Prompts](https://awesome-repositories.com/f/devops-infrastructure/recurring-job-scheduling/agent-run-scheduling/recurring-wake-prompts.md) — Defines a recurring wake prompt contract so long-running goals resume across sessions without a person restarting them. ([source](https://github.com/loopx-project/loopx/blob/main/docs/README.md))

### Security & Cryptography

- [Durable Control-Plane State for Ephemeral Executors](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/agentic-session-persistence/durable-control-plane-state-for-ephemeral-executors.md) — Keeps goals and project intent in durable control-plane state while executor sessions stay ephemeral, so each turn starts clean. ([source](https://loopx-project.github.io/loopx/benchmarks/swe-marathon/))
- [Per-Goal Agent Compute Quotas](https://awesome-repositories.com/f/security-cryptography/governance-policy-frameworks/security-infrastructure/multi-tenant-security/compute-quota-management/per-goal-agent-compute-quotas.md) — Assigns each goal an automatic-compute allowance with a spend ledger and allocation states that automations check before running. ([source](https://github.com/loopx-project/loopx/blob/main/docs/quota-allocation.md))
- [Agentic Session Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/agentic-session-persistence.md) — Keeps goals and project state in durable storage outside the agent session so each new turn starts clean but retains original intent. ([source](https://loopx-project.github.io/loopx/benchmarks/swe-marathon/))

### Software Engineering & Architecture

- [Receipt-Based Turn Settlement](https://awesome-repositories.com/f/software-engineering-architecture/receipt-based-turn-settlement.md) — Orders each turn as validate, writeback, quota spend and close-out with identity-bound receipts so crashes resume without duplicate retries. ([source](https://loopx-project.github.io/loopx/blog/from-one-shot-agents-to-long-horizon-control/))
- [Atomic Lease Claims](https://awesome-repositories.com/f/software-engineering-architecture/atomic-lease-claims.md) — Commits the task claim, execution lease and operation receipt together in one conditional transaction, so no half-claimed state exists between agents. ([source](https://loopx-project.github.io/loopx/blog/typescript-control-plane-refactor/))
- [Host-Native Loop Launching](https://awesome-repositories.com/f/software-engineering-architecture/client-server-architecture/long-running-task-protocols/agentic-planning-loops/host-native-loop-launching.md) — Starts long-running tasks from an existing agent session, plans them into todos, and activates the host's native continuation mechanism. ([source](https://github.com/loopx-project/loopx/blob/main/README.zh-CN.md))
- [Kernel-Preserving Extension Layers](https://awesome-repositories.com/f/software-engineering-architecture/extensibility-patterns/protocol-extensions/capability-extensions/kernel-preserving-extension-layers.md) — Separates capabilities, providers and extensions with their own lifecycles so optional integrations are added without changing the kernel's authority and acceptance rules. ([source](https://loopx-project.github.io/loopx/blog/from-one-shot-agents-to-long-horizon-control/))
- [Outcome-Owned Capability Lanes](https://awesome-repositories.com/f/software-engineering-architecture/extensibility-patterns/protocol-extensions/capability-extensions/outcome-owned-capability-lanes.md) — Packages repeatable workflows such as issue fixing, change-quality review and periodic reporting into outcome-owned lanes with declared write boundaries and readiness checks. ([source](https://github.com/loopx-project/loopx/blob/main/README.zh-CN.md))
- [Replaceable Integration Providers](https://awesome-repositories.com/f/software-engineering-architecture/extensibility-patterns/protocol-extensions/capability-extensions/replaceable-integration-providers.md) — Connects Git hosts, CI services and notifiers through replaceable providers behind stable capability contracts, shipped as independently installable extensions. ([source](https://github.com/loopx-project/loopx/blob/main/docs/development/control-plane-course/00-concept-primer.md))
- [Issue-to-Merge Fix Loops](https://awesome-repositories.com/f/software-engineering-architecture/reproducibility-verifiers/automated-fix-verifiers/issue-to-merge-fix-loops.md) — Drives an issue through fix, monitoring, review correction, user gate and terminal states, gating each step on checks, review and merge state. ([source](https://github.com/loopx-project/loopx/blob/main/docs/development/control-plane-course/README.md))
- [Local Write Fencing](https://awesome-repositories.com/f/software-engineering-architecture/shared-caching-topologies/shared-cache-write-permissions/local-write-fencing.md) — Uses per-todo leases, idempotency keys and revision checks so concurrent writers, duplicate heartbeats and stale updates fail closed, with a CLI fallback when the coordinator is down. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture.md))
- [Validate-Then-Commit State Transitions](https://awesome-repositories.com/f/software-engineering-architecture/validate-then-commit-state-transitions.md) — Treats provider observations as proposals until validated and committed by the kernel, keeping domain reasoning, external calls and durable lifecycle separate. ([source](https://github.com/loopx-project/loopx/blob/main/docs/architecture.md))

### Business & Productivity Software

- [Agent Task Board Mirrors](https://awesome-repositories.com/f/business-productivity-software/collaborative-project-planning/agent-task-board-mirrors.md) — Mirrors todos and decisions onto external collaboration surfaces such as a chat-based kanban while the local control plane remains authoritative. ([source](https://github.com/loopx-project/loopx#readme))
- [Human and Agent Todo Assignment](https://awesome-repositories.com/f/business-productivity-software/human-and-agent-todo-assignment.md) — Creates, lists and updates todos assigned to people or agents, keeping task ownership in durable state outside any chat. ([source](https://loopx-project.github.io/loopx/docs/))
- [Shared Human-Agent Workspaces](https://awesome-repositories.com/f/business-productivity-software/shared-human-agent-workspaces.md) — Brings people into agent work through a personal workspace and chat channels so they can steer, correct and review agents. ([source](https://loopx-project.github.io/loopx/blog/long-horizon-rsi/))

### Data & Databases

- [External State Stores](https://awesome-repositories.com/f/data-databases/external-state-stores.md) — Persists goals, todos, claims, gates, quota and evidence in a local registry outside any chat session so work survives restarts and runtime swaps.

### Development Tools & Productivity

- [Agent Host Adapters](https://awesome-repositories.com/f/development-tools-productivity/agent-host-adapters.md) — Provides thin per-host adapters connecting agent turns to Codex, Claude Code, Kiro CLI and custom runners so one team coordinates across runtimes. ([source](https://github.com/loopx-project/loopx/tree/main/scripts))