cd /news/ai-agents/agent-swarm-oss-multiplayer-ai-for-y… · home › topics › ai-agents › article
[ARTICLE · art-148342] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Agent Swarm: OSS multiplayer AI for your company

Desplega AI released Agent Swarm v1.167.0, an open-source multi-agent orchestration platform, published to npm as @desplega.ai/agent-swarm and to GitHub Container Registry as separate server, worker, and dashboard images. The release includes fixes for ACP target configuration validation, Codex OAuth token refresh timing, and Codex context reporting, plus a heartbeat change that skips the Lead boot-triage task on a clean boot. The project also ships E2B templates tagged agent-swarm-api-1-167-0 and agent-swarm-worker-1-167-0.

read19 min views3 publishedOct 9, 2026
Agent Swarm: OSS multiplayer AI for your company
Image: Michielbdejong (auto-discovered)

Repository navigation #

Release list #

v1.167.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.167.0
npm i -g @desplega.ai/agent-swarm@1.167.0

bun:

bunx @desplega.ai/agent-swarm@1.167.0
bun i -g @desplega.ai/agent-swarm@1.167.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.167.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.167.0
docker pull ghcr.io/desplega-ai/agent-swarm-ui:1.167.0

E2B templates:

agent-swarm-api-1-167-0
agent-swarm-api-latest

agent-swarm-worker-1-167-0
agent-swarm-worker-latest

What's Changed #

Full Changelog: v1.166.0...v1.167.0

v1.166.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.166.0
npm i -g @desplega.ai/agent-swarm@1.166.0

bun:

bunx @desplega.ai/agent-swarm@1.166.0
bun i -g @desplega.ai/agent-swarm@1.166.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.166.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.166.0
docker pull ghcr.io/desplega-ai/agent-swarm-ui:1.166.0

E2B templates:

agent-swarm-api-1-166-0
agent-swarm-api-latest

agent-swarm-worker-1-166-0
agent-swarm-worker-latest

What's Changed #

  • chore(maintenance): versioned retro-sweep across logs, memory, tasks, events and workflow steps by @desplega-bot in#1917
  • feat(secrets): central secret registry with a combined known-value matcher by @desplega-bot in#1918
  • feat(scrubber): vendored gitleaks rule set with keyword prefilter and corpus test by @desplega-bot in#1922
  • feat(db): ScrubbedText write contract and TEXT-column classification check by @desplega-bot in#1923
  • fix: de-flake adversarial scrubber timing guard by @desplega-bot in#1966
  • fix(db): scrub event payloads at write by @desplega-bot in#1924
  • fix(db): scrub script run args, output and errors at write by @desplega-bot in#1925
  • fix(docs): correct Linear gate docs — empty LINEAR_ALLOWED_STATES closes the gate by @sqmyou in#1965
  • chore(docker): bump claude-code, codex, cursor, amp, anthropic sdk (2026-10-07) by @desplega-bot in#1967
  • feat(scripts): opt-in quickjs script executor by @tarasyarema in#1951
  • feat(acp): add a copilot ACP target for GitHub Copilot CLI by @desplega-bot in#1957
  • fix(db): scrub workflow run and step payloads at write by @desplega-bot in#1926
  • fix(db): scrub memory, messages, approvals, schedules and task text at write by @desplega-bot in#1927
  • test(security): canary sweep across every table and stdout by @desplega-bot in#1928
  • fix: typecheck QuickJS worker in extension SDK bundler by @desplega-bot in#1969
  • fix(db-query): deny credential tables and scrub the HTTP route by @desplega-bot in#1915
  • release: v1.166.0 + docs daily update 2026-10-08 by @desplega-bot in#1970

New Contributors #

Full Changelog: v1.165.0...v1.166.0

v1.165.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.165.0
npm i -g @desplega.ai/agent-swarm@1.165.0

bun:

bunx @desplega.ai/agent-swarm@1.165.0
bun i -g @desplega.ai/agent-swarm@1.165.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.165.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.165.0
docker pull ghcr.io/desplega-ai/agent-swarm-ui:1.165.0

E2B templates:

agent-swarm-api-1-165-0
agent-swarm-api-latest

agent-swarm-worker-1-165-0
agent-swarm-worker-latest

What's Changed #

  • docs(specs): sync TLA+ specs with main (heartbeat) by @desplega-bot in#1933
  • fix(heartbeat): exclude all terminal statuses from deduplication by @desplega-bot in#1909
  • chore(docker): bump amp (2026-10-07) by @desplega-bot in#1931
  • perf(ci): skip merge-queue image load, typecheck with tsgo, add bun run check by @desplega-bot in#1920
  • fix(egress): scrub Slack and WhatsApp sends at the client by @desplega-bot in#1919
  • fix(scrubber): bare and case-insensitive keys, structured key-context rules, PEM and URL credentials by @desplega-bot in#1916
  • fix(ui): show self-hosted support links by @desplega-bot in#1936
  • feat(pr-template): show-me PR template with review map, risk and swarm provenance by @desplega-bot in#1937
  • fix(scripts): call back through the internal base url for background runs and codex keep-warm by @oscar-izval in#1935
  • feat(users): one-click Connect to ChatGPT via single-use connector codes by @tarasyarema in#1903
  • feat(logging): process-wide console scrub at API and worker boot by @desplega-bot in#1921
  • fix(skills): use OAuth bindings for Jira and Linear by @desplega-bot in#1929
  • fix(pr-body): track fence and HTML comment state before opening Swarm provenance by @desplega-bot in#1938
  • chore(skills): re-sync vendored qa skill from ai-toolbox 77abe63 by @desplega-bot in#1942
  • feat(ui): inline /connect confirm step instead of a dialog by @tarasyarema in#1944
  • feat(workflows): openai and cloudflare clef providers for system-one-decision by @desplega-bot in#1945
  • feat(docker): publish the dashboard as an nginx image by @oscar-izval in#1943
  • chore(deps): bump nginxinc/nginx-unprivileged from 1.29.8-alpine to 1.31.5-alpine by @dependabot [bot] in#1946
  • chore(ci): remove HOL plugin scanner workflow by @desplega-bot in#1950
  • fix: parse integration *_DISABLE flags with the shared env-flag parser by @azmi2409 in#1948
  • fix(mcp): per-channel result budget, spill shape summary and kv-get views by @desplega-bot in#1949
  • test: drop Anthropic credentials from the test env by @tarasyarema in#1954
  • feat(acp): add a gemini ACP target that runs gemini --acp by @desplega-bot in#1956
  • refactor(pages): add a guest principal for page sessions by @oscar-izval in#1955
  • fix(credentials): honor pi and opencode presence-only credentials by @ZedingZhang in#1960
  • fix(memory): show outcome and date in injected memories, expire legacy auto-memories by @desplega-bot in#1963
  • feat(providers): grok CLI harness (API key) by @desplega-bot in#1959
  • fix: route user MCP tasks through the Lead by @tarasyarema in#1964
  • release: v1.165.0 by @desplega-bot in#1961

New Contributors #

Full Changelog: v1.164.1...v1.165.0

v1.164.1 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.164.1
npm i -g @desplega.ai/agent-swarm@1.164.1

bun:

bunx @desplega.ai/agent-swarm@1.164.1
bun i -g @desplega.ai/agent-swarm@1.164.1

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.164.1
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.164.1

E2B templates:

agent-swarm-api-1-164-1
agent-swarm-api-latest

agent-swarm-worker-1-164-1
agent-swarm-worker-latest

What's Changed #

New Contributors #

Full Changelog: v1.164.0...v1.164.1

v1.164.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.164.0
npm i -g @desplega.ai/agent-swarm@1.164.0

bun:

bunx @desplega.ai/agent-swarm@1.164.0
bun i -g @desplega.ai/agent-swarm@1.164.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.164.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.164.0

E2B templates:

agent-swarm-api-1-164-0
agent-swarm-api-latest

agent-swarm-worker-1-164-0
agent-swarm-worker-latest

What's Changed #

  • docs: Release Notes — Week of September 28 to October 5, 2026 by @desplega-bot in#1867
  • docs(workflows): state that bash script args[0] binds to $0 by @desplega-bot in#1870
  • dreaming-v2 systemDefault skill seed patches (2026-10-05) by @desplega-bot in#1871
  • fix(github): skip the lead task for approvals with nothing to act on by @desplega-bot in#1872
  • docs(specs): sync TLA+ specs with main (heartbeat) by @desplega-bot in#1873
  • chore(docker): bump pi (2026-10-05) by @desplega-bot in#1874
  • feat(approvals): take the responder from the credential and enforce the approvers policy by @desplega-bot in#1854
  • fix(gitlab): emit documented past-tense workflow event names by @knownshah in#1880
  • feat(extensions): bridge approval, budget, email, Kapso and code-host events as post.* events by @desplega-bot in#1878
  • fix(heartbeat): refresh a task's session liveness from session-log ingestion by @desplega-bot in#1879
  • fix: use script endpoint for nightly coverage by @desplega-bot in#1884
  • feat(providers): add a native cursor harness on @cursor/sdk by @desplega-bot in#1882
  • fix(x402): reserve spending before payment creation so concurrent payments can't overshoot the daily limit by @domondi1 in#1885
  • feat(providers): add a native amp harness (Amp CLI, stream-json) by @desplega-bot in#1883
  • fix(cursor): exclude cache writes from fresh input tokens by @desplega-bot in#1886
  • fix(amp): deliver queued steering at the next tool result, fail unknown pins fast by @desplega-bot in#1887
  • chore(docker): bump codex, cursor, amp (2026-10-05) by @desplega-bot in#1888
  • feat(ui): task detail page overhaul (desktop + mobile) by @tarasyarema in#1881
  • release: v1.164.0 + docs daily update 2026-10-06 by @desplega-bot in#1889

New Contributors #

Full Changelog: v1.163.0...v1.164.0

v1.163.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.163.0
npm i -g @desplega.ai/agent-swarm@1.163.0

bun:

bunx @desplega.ai/agent-swarm@1.163.0
bun i -g @desplega.ai/agent-swarm@1.163.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.163.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.163.0

E2B templates:

agent-swarm-api-1-163-0
agent-swarm-api-latest

agent-swarm-worker-1-163-0
agent-swarm-worker-latest

What's Changed #

  • fix(rbac): require lead, operator or user for stdio MCP servers at agent scope by @desplega-bot in#1851
  • fix(rbac): require lead, operator or user to change a repo's allowMerge by @desplega-bot in#1852
  • fix(rbac): require lead, operator or user to attribute a task to another user by @desplega-bot in#1853
  • fix(tests): isolate inherited Claude transport in adapter tests by @desplega-bot in#1858
  • feat(memory): gate HTTP memory delete and narrow list for agent callers by @desplega-bot in#1855
  • fix(memory): remove stale chunks when deleting keyed documents by @desplega-bot in#1857
  • feat(ui): replace task status dots and spinners with the reference icon set by @desplega-bot in#1860
  • fix(rbac): decide stdio and allowMerge updates inside the write transaction by @desplega-bot in#1859
  • feat(ui): longterm key tree and whole-memory view on /memory by @desplega-bot in#1856
  • fix(memory): resolve a key-only chunk lookup to one visible document by @desplega-bot in#1861
  • docs: correct workflow example configs and routing by @desplega-bot in#1862
  • docs: align SSO RBAC note, Sentry summary, and compose service table with code by @desplega-bot in#1863
  • docs: add multi-agent orchestration patterns guide by @desplega-bot in#1864
  • docs: add features section with a team collaboration page by @desplega-bot in#1865
  • fix(ui): offer a reload instead of crashing when a deploy removes a lazy chunk by @desplega-bot in#1866
  • release: v1.163.0 + docs daily update 2026-10-05 by @desplega-bot in#1869

Full Changelog: v1.162.0...v1.163.0

v1.162.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.162.0
npm i -g @desplega.ai/agent-swarm@1.162.0

bun:

bunx @desplega.ai/agent-swarm@1.162.0
bun i -g @desplega.ai/agent-swarm@1.162.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.162.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.162.0

E2B templates:

agent-swarm-api-1-162-0
agent-swarm-api-latest

agent-swarm-worker-1-162-0
agent-swarm-worker-latest

What's Changed #

Full Changelog: v1.161.0...v1.162.0

v1.161.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.161.0
npm i -g @desplega.ai/agent-swarm@1.161.0

bun:

bunx @desplega.ai/agent-swarm@1.161.0
bun i -g @desplega.ai/agent-swarm@1.161.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.161.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.161.0

E2B templates:

agent-swarm-api-1-161-0
agent-swarm-api-latest

agent-swarm-worker-1-161-0
agent-swarm-worker-latest

What's Changed #

  • fix(claude-managed): migrate to @anthropic-ai/sdk ^0.131.0 by @desplega-bot in#1805
  • fix(memory): pin the memory rater model and record it per rating by @desplega-bot in#1806
  • docs(playbooks): add open-prompt showreel videos playbook by @desplega-bot in#1809
  • fix(claude): send the task body once in the first message by @desplega-bot in#1815
  • fix(memory): accept a blank referencesSource instead of rejecting the whole summary by @desplega-bot in#1807
  • fix(dsh): MCP, failure path, sandbox, cost/context, effort, and runtime editing by @desplega-bot in#1810
  • chore(docker): bump ACP (2026-10-01) by @desplega-bot in#1811
  • fix(github): react 👀 on pings via GITHUB_TOKEN when no GitHub App is installed by @desplega-bot in#1813
  • feat(db-retention): count-based retention for context_versions by @desplega-bot in#1808
  • feat(integrations): add minimal Azure DevOps integration (Azure Repos + PR service hooks) by @desplega-bot in#1812
  • feat(e2e): collapse Slack rendering preview comment into one dropdown by @desplega-bot in#1817
  • fix(dsh): readable progress, one usage normalization, no phantom cost drift by @desplega-bot in#1818
  • feat(memory): logical paths under /longterm via key, newKey, keyPrefix and path weight by @desplega-bot in#1814
  • feat(claude): accept gateway, Foundry, Bedrock and Vertex routes by @desplega-bot in#1816
  • fix(runner): free a worker slot when the provider session never settles by @desplega-bot in#1820
  • fix(runner): report pi CLI versions and clear stale harness versions by @desplega-bot in#1821
  • fix(mcp): answer unknown MCP session ids with 404 so clients reconnect by @tarasyarema in#1822
  • fix(azure-devops): ack payloads missing resource fields instead of 500 by @desplega-bot in#1823
  • feat(pi): PI_CODEMODE_MODELS flag and pi 1.0 power-use pilot by @desplega-bot in#1824
  • feat(extensions): add deploy-awareness catalog extension by @desplega-bot in#1826
  • chore(docker): bump claude-code, pi, codex (2026-10-01) by @desplega-bot in#1825
  • feat(extensions): opt-in inline install for leads and operators by @desplega-bot in#1828
  • release: v1.161.0 + docs daily update 2026-10-02 by @desplega-bot in#1830

Full Changelog: v1.160.0...v1.161.0

v1.160.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.160.0
npm i -g @desplega.ai/agent-swarm@1.160.0

bun:

bunx @desplega.ai/agent-swarm@1.160.0
bun i -g @desplega.ai/agent-swarm@1.160.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.160.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.160.0

E2B templates:

agent-swarm-api-1-160-0
agent-swarm-api-latest

agent-swarm-worker-1-160-0
agent-swarm-worker-latest

What's Changed #

  • docs(specs): sync TLA+ specs with main (heartbeat, workflows) by @desplega-bot in#1738
  • fix(seed): treat source-identical live copy as in sync before pristine check by @desplega-bot in#1734
  • chore(docker): bump codex (2026-09-30) by @desplega-bot in#1735
  • fix(seed-scripts): project failure reasons for every task-failure-audit groupBy by @desplega-bot in#1736
  • fix(store-progress): refuse writes to another agent's task by @desplega-bot in#1737
  • fix(prompts): gate tool-search guidance by harness capability by @desplega-bot in#1727
  • docs(model-catalog): verify task returns overlayProposals, one refresh covers both vendors by @desplega-bot in#1733
  • feat(evals): suite v1 freeze, grader validation, attempt hygiene (Phase 3) by @desplega-bot in#1741
  • feat(evals): fan-out and worker-recovery swarm scenarios with solo baselines (Phase 7) by @desplega-bot in#1745
  • fix(ci): wait for late Dokploy deployment records and retrigger when none appears by @desplega-bot in#1742
  • fix(memory): recall task content instead of worker wrappers by @desplega-bot in#1740
  • fix(ui): resolve dashboard UI audit action items by @desplega-bot in#1743
  • chore(deps): bump agent-fs to 0.15.0 by @tarasyarema in#1748
  • feat(evals): analytics API for picking the best setup (Phase 4) by @desplega-bot in#1744
  • fix(opencode): send X-Source-Task-Id and X-Context-Key on the swarm MCP entry by @desplega-bot in#1749
  • docs(workflows): how to use system-one-decision with provider laya by @desplega-bot in#1750
  • feat(opencode): validate the final assistant message against outputSchema by @desplega-bot in#1753
  • ci(ui-e2e): time out and retry stuck artifact uploads by @tarasyarema in#1754
  • feat(pi): defer non-core swarm tools behind tool_search and pass structuredContent by @desplega-bot in#1729
  • feat(pi): connect installed MCP servers through pi's MCP extension by @desplega-bot in#1730
  • feat(evals): Leaderboard home with Pareto frontier and ranking table (Phase 5) by @desplega-bot in#1755
  • docs: add dashboard design reference by @desplega-bot in#1757
  • feat(evals): Scenario cards, heatmap, reliability and run outcome (Phase 6) by @desplega-bot in#1759
  • feat(workflows): add standard-webhooks verification mode for webhook triggers by @desplega-bot in#1760
  • feat(pi): opt-in codemode behind PI_CODEMODE by @desplega-bot in#1731
  • feat(evals): Phase 8 swarm scenarios — implement-review, capability-routing, human-in-loop by @desplega-bot in#1756
  • feat(evals): publishable benchmark v1.0 page and refusal-gated publish (Phase 10) by @desplega-bot in#1761
  • fix(telemetry): honor the opt-out in dashboard events and correct telemetry docs by @desplega-bot in#1773
  • feat(evals): run codex on the ChatGPT subscription, add gpt-6.1-sol and gpt-5.6, schedule public cells first by @desplega-bot in#1772
  • feat(model): reject a task model that the assignee harness cannot run by @fuvidani in#1764
  • fix(pi): run codemode in the compiled binary and unset deleted reloadable config by @desplega-bot in#1767
  • feat(slack): native working status for the whole life of an ask by @desplega-bot in#1770
  • feat(evals-ui): way back from /benchmark and an always-on Pareto line by @desplega-bot in#1771
  • fix(evals): copy the codex OAuth helpers into the evals image by @desplega-bot in#1778
  • fix(ui): resolve swarm UI audit v2 findings by @desplega-bot in#1774
  • fix(docs-site): fix the docs UI audit findings by @desplega-bot in#1776
  • chore(test): raise the db.ts line cap to 14400 until a frozen-body rule lands by @desplega-bot in#1783
  • fix(credentials): bench a Codex pool login after 2 auth failures in a row by @fuvidani in#1763
  • fix(boot): linear memory_fts backfill and retried worker registration by @desplega-bot in#1791
  • chore(test): freeze db.ts top-level bodies instead of capping its line count by @desplega-bot in#1784
  • fix(credentials): seat-aware Claude OAuth key selection for Fable by @fuvidani in#1765
  • docs(specs): sync TLA+ specs with main (heartbeat) by @desplega-bot in#1798
  • chore(docker): bump claude-code, pi, codex, opencode (2026-10-01) by @desplega-bot in#1792
  • fix(ci): stop the pi version probe from wedging test workers by @desplega-bot in#1795
  • docs: correct Codex plugin installation command by @desplega-bot in#1790
  • feat(evals): add real-diff-agent-fs scenario (a real merged fix, pushed and graded by hidden tests) by @desplega-bot in#1796
  • chore(deps): bump vulnerable docs-site dependencies (Dependabot alerts) by @desplega-bot in#1799
  • chore(deps): bump vulnerable apps/templates-ui dependencies (Dependabot alerts) by @desplega-bot in#1802
  • chore(deps): bump agent-fs image to 0.15.0 by @desplega-bot in#1803
  • release: v1.160.0 + docs daily update 2026-10-01 by @desplega-bot in#1797
  • chore(docker): bump dsh, ACP (2026-10-01) by @desplega-bot in#1804

Full Changelog: v1.159.0...v1.160.0

v1.159.0 #

Install & Run #

npm:

npx @desplega.ai/agent-swarm@1.159.0
npm i -g @desplega.ai/agent-swarm@1.159.0

bun:

bunx @desplega.ai/agent-swarm@1.159.0
bun i -g @desplega.ai/agent-swarm@1.159.0

Docker:

docker pull ghcr.io/desplega-ai/agent-swarm:1.159.0
docker pull ghcr.io/desplega-ai/agent-swarm-worker:1.159.0

E2B templates:

agent-swarm-api-1-159-0
agent-swarm-api-latest

agent-swarm-worker-1-159-0
agent-swarm-worker-latest

What's Changed #

Full Changelog: v1.158.0...v1.159.0

source & further reading
github.com — original article Show HN: Narwhal – LLM serving that moves GPUs between prefill/decode in seconds Speakoflow – Free Voice Dictation and AI Assistant for Windows, macOS, and Linux Solving Anubis's SHA-256 Proof-of-Work Challenge
── more in #ai-agents 4 stories · sorted by recency
── more on @desplega ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agent-swarm-oss-mult…] indexed:0 read:19min 2026-10-09 · —