You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: changelog/overview.mdx
+78-35Lines changed: 78 additions & 35 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,6 @@ mode: "wide"
4
4
---
5
5
6
6
<Updatelabel="2025-04-23"description="v1.4.0">
7
-
#
8
7
9
8
## New Features:
10
9
@@ -24,8 +23,10 @@ mode: "wide"
24
23
## Breaking Changes:
25
24
26
25
-**Memory:** Agents will now by default use an improved `Memory` instead of the now deprecated `AgentMemory`. - `agent.memory.messages` → `run.messages for run in agent.memory.runs` (or `agent.get_messages_for_session()`) - `create_user_memories` → `enable_user_memories` and is now set on the Agent/Team directly. - `create_session_summary` → `enable_session_summaries` and is now set on the Agent/Team directly.
27
-
</Update>
28
-
<Updatelabel="2025-04-21"description="v1.3.5">
26
+
27
+
</Update>
28
+
29
+
<Updatelabel="2025-04-21"description="v1.3.5">
29
30
30
31
## Improvements:
31
32
@@ -45,8 +46,10 @@ mode: "wide"
45
46
## Bug Fixes
46
47
47
48
-**Firecrawl Scrape**: Fixed issues with non-serializable types for during Firecrawl execution. https://github.com/agno-agi/agno/issues/2883
48
-
</Update>
49
-
<Updatelabel="2025-04-18"description="v1.3.4">
49
+
50
+
</Update>
51
+
52
+
<Updatelabel="2025-04-18"description="v1.3.4">
50
53
51
54
## New Features:
52
55
@@ -68,8 +71,10 @@ mode: "wide"
68
71
69
72
-**DynamoDB Storage:** Fixed an issue with storage handling in DynamoDB-based setups.
70
73
-**DeepSeek:** Fixed a bug with API key validation logic.
71
-
</Update>
72
-
<Updatelabel="2025-04-17"description="v1.3.3">
74
+
75
+
</Update>
76
+
77
+
<Updatelabel="2025-04-17"description="v1.3.3">
73
78
74
79
## Improvements:
75
80
@@ -81,9 +86,11 @@ mode: "wide"
81
86
82
87
-**PPrint Util Async**: Added `apprint_run_response` to support async.
83
88
-**Mistral Reasoning:** Fixed issues with using a Mistral model for chain-of-thought reasoning.
84
-
</Update>
89
+
90
+
</Update>
85
91
86
92
<Updatelabel="2025-04-16"description="v1.3.2">
93
+
87
94
## New Features:
88
95
89
96
-**Redis Memory DB**: Added Redis as a storage provider for `Memory`. See [here](https://docs.agno.com/examples/concepts/memory/mem-redis-memory).
@@ -102,7 +109,8 @@ mode: "wide"
102
109
-**LiteLLM Streaming Tool Calls**: Fixed issues with tool call streaming in LiteLLM.
103
110
-**E2B Casing Issue**: Fixed issues with parsed Python code that would make some values lowercase.
104
111
-**Team Member IDs**: Fixed edge-cases with team member IDs causing teams to break.
105
-
</Update>
112
+
113
+
</Update>
106
114
107
115
<Updatelabel="2025-04-12"description="v1.3.0">
108
116
## New Features:
@@ -139,7 +147,8 @@ mode: "wide"
139
147
-**ChromaDB Version Compatibility:** Fix to ensure that ChromaDB and Agno are compatible with newer versions of ChromaDB.
140
148
-**Team-Member Interactions**: Fixed issue where if members respond with empty content the team would halt. This is now be resolved.
141
149
-**Claude Empty Response:** Fixed a case when the response did not include any content with tool calls resulting in an error from the Anthropic API
142
-
</Update>
150
+
151
+
</Update>
143
152
144
153
<Updatelabel="2025-04-07"description="v1.2.12">
145
154
## New Features:
@@ -151,29 +160,33 @@ mode: "wide"
151
160
## Improvements:
152
161
153
162
-**Async Vector DB and Knowledge Base Improvements**: More knowledge bases have been updated for `async-await` support: - `URLKnowledgeBase` → Find some examples [here](https://github.com/agno-agi/agno/blob/9d1b14af9709dde1e3bf36c241c80fb295c3b6d3/cookbook/agent_concepts/knowledge/url_kb_async.py). - `FireCrawlKnowledgeBase` → Find some examples [here](https://github.com/agno-agi/agno/blob/596898d5ba27d2fe228ea4f79edbe9068d34a1f8/cookbook/agent_concepts/knowledge/firecrawl_kb_async.py). - `DocxKnowledgeBase` → Find some examples [here](https://github.com/agno-agi/agno/blob/f6db19f4684f6ab74044a4466946e281586ca1cf/cookbook/agent_concepts/knowledge/docx_kb_async.py).
154
-
</Update>
163
+
164
+
</Update>
155
165
156
166
<Updatelabel="2025-04-07"description="v1.2.11">
157
167
## Bug Fixes:
158
168
159
169
-**Fix for structured outputs**: Fixed cases of structured outputs for reasoning.
160
-
</Update>
170
+
171
+
</Update>
161
172
162
173
<Updatelabel="2025-04-07"description="v1.2.10">
163
174
## 1.2.10
164
175
165
176
## New Features:
166
177
167
178
-**Knowledge Tools**: Added `KnowledgeTools` for thinking, searching and analysing documents in a knowledge base.
168
-
</Update>
179
+
180
+
</Update>
169
181
170
182
<Updatelabel="2025-04-05"description="v1.2.9">
171
183
## 1.2.9
172
184
173
185
## Improvements:
174
186
175
187
-**Simpler MCP Interface**: Added `MultiMCPTools` to support multiple server connections and simplified the interface to allow `command` to be passed. See [these examples](https://github.com/agno-agi/agno/blob/382667097c31fbb9f08783431dcac5eccd64b84a/cookbook/tools/mcp) of how to use it.
176
-
</Update>
188
+
189
+
</Update>
177
190
178
191
<Updatelabel="2025-04-04"description="v1.2.8">
179
192
## 1.2.8
@@ -187,8 +200,10 @@ mode: "wide"
187
200
## Bug Fixes:
188
201
189
202
-**Teams transfer functions**: Some tool definitions of teams failed for certain models. This has been fixed.
190
-
</Update>
191
-
<Updatelabel="2025-04-02"description="v1.2.7">
203
+
204
+
</Update>
205
+
206
+
<Updatelabel="2025-04-02"description="v1.2.7">
192
207
193
208
## 1.2.7
194
209
@@ -219,7 +234,8 @@ mode: "wide"
219
234
## Bug Fixes:
220
235
221
236
-**Recursive Chunking Infinite Loop**: Fixes an issue with RecursiveChunking getting stuck in an infinite loop for large documents.
222
-
</Update>
237
+
238
+
</Update>
223
239
224
240
<Updatelabel="2025-03-28"description="v1.2.6">
225
241
## 1.2.6
@@ -230,7 +246,9 @@ mode: "wide"
230
246
-**Reasoning fix**: Fixed an issue with default reasoning and improved logging for reasoning models .
231
247
232
248
</Update>
249
+
233
250
<Updatelabel="2025-03-27"description="v1.2.5">
251
+
234
252
## 1.2.5
235
253
236
254
## New Features:
@@ -252,6 +270,7 @@ mode: "wide"
252
270
-**Worklow session retrieval from storage**: Fixed `entity_id` mappings.
253
271
254
272
</Update>
273
+
255
274
<Updatelabel="2025-03-25"description="v1.2.4">
256
275
## 1.2.4
257
276
@@ -263,31 +282,36 @@ mode: "wide"
263
282
264
283
-**Sessions not created**: Made issue where sessions would not be created in existing tables without a migration be more visible. Please read the docs on [storage schema migrations](https://docs.agno.com/agents/storage).
265
284
-**Todoist fixes**: Fixed `update_task` on `TodoistTools`.
266
-
</Update>
285
+
286
+
</Update>
267
287
268
288
<Updatelabel="2025-03-24"description="v1.2.3">
269
289
## 1.2.3
270
290
271
291
## Improvements:
272
292
273
293
-**Teams Error Handling:** Improved the flow in cases where the model gets it wrong when forwarding tasks to members.
274
-
</Update>
275
-
<Updatelabel="2025-03-24"description="v1.2.2">
294
+
295
+
</Update>
296
+
297
+
<Updatelabel="2025-03-24"description="v1.2.2">
276
298
277
299
## 1.2.2
278
300
279
301
## Bug Fixes:
280
302
281
303
-**Teams Memory:** Fixed issues related to memory not persisting correctly across multiple sessions.
282
-
</Update>
304
+
305
+
</Update>
283
306
284
307
<Updatelabel="2025-03-24"description="v1.2.1">
285
308
## 1.2.1
286
309
287
310
## Bug Fixes:
288
311
289
312
-**Teams Markdown**: Fixed issue with markdown in teams responses.
290
-
</Update>
313
+
314
+
</Update>
291
315
292
316
<Updatelabel="2025-03-24"description="v1.2.0">
293
317
## 1.2.0
@@ -305,15 +329,17 @@ mode: "wide"
305
329
## Bug Fixes:
306
330
307
331
-**Azure AI Factory:** Fix for a broken import in Azure AI Factory.
308
-
</Update>
332
+
333
+
</Update>
309
334
310
335
<Updatelabel="2025-03-23"description="v1.1.17">
311
336
## 1.1.17
312
337
313
338
## Improvements:
314
339
315
340
-**Better Debug Logs**: Enhanced debug logs for better readability and clarity.
316
-
</Update>
341
+
342
+
</Update>
317
343
318
344
<Updatelabel="2025-03-22"description="v1.1.16">
319
345
## 1.1.16
@@ -341,7 +367,8 @@ mode: "wide"
341
367
- Websitetools
342
368
- YFinanceTools
343
369
-**Show tool calls**: Improved how tool calls are displayed when `print_response` and `aprint_response` is used. They are now displayed in a separate panel different from response panel. It can also be used in conjunction in `response_model`.
344
-
</Update>
370
+
371
+
</Update>
345
372
346
373
<Updatelabel="2025-03-20"description="v1.1.14">
347
374
## 1.1.14 - Teams Revamp
@@ -375,6 +402,7 @@ mode: "wide"
375
402
-**Agent Team:**`Agent.team` is deprecated with the release of our new Teams implementation [here](https://docs.agno.com/teams/introduction). This will be removed in a future major version release.
376
403
377
404
</Update>
405
+
378
406
<Updatelabel="2025-03-14"description="v1.1.13">
379
407
## 1.1.13
380
408
@@ -392,6 +420,7 @@ mode: "wide"
392
420
-**Google Maps Places**: Support from Google for Places API has been changed and this brings it up to date so we can continue to support “search places”.
393
421
394
422
</Update>
423
+
395
424
<Updatelabel="2025-03-13"description="v1.1.12">
396
425
## 1.1.12
397
426
@@ -408,6 +437,7 @@ mode: "wide"
408
437
-**MemoryManager**: Limit parameter was added fixing a KeyError in MongoMemoryDb.
409
438
410
439
</Update>
440
+
411
441
<Updatelabel="2025-03-13"description="v1.1.11">
412
442
## 1.1.11
413
443
@@ -421,6 +451,7 @@ mode: "wide"
421
451
-**Storage Refactor:** Merged agent and workflow storage classes to align storage better for agents, teams and workflows. This change is backwards compatible and should not result in any disruptions.
422
452
423
453
</Update>
454
+
424
455
<Updatelabel="2025-03-12"description="v1.1.10">
425
456
## 1.1.10
426
457
@@ -456,6 +487,7 @@ mode: "wide"
456
487
-**Mistral with reasoning**: Fixed cases where Mistral would fail when reasoning models from other providers generated reasoning content.
457
488
458
489
</Update>
490
+
459
491
<Updatelabel="2025-03-03"description="v1.1.8">
460
492
## 1.1.8
461
493
@@ -482,6 +514,7 @@ mode: "wide"
482
514
-**Claude Thinking Streaming**: Fix Claude thinking when streaming is active, as well as for async runs.
483
515
484
516
</Update>
517
+
485
518
<Updatelabel="2025-02-24"description="v1.1.6">
486
519
## 1.1.6
487
520
@@ -544,7 +577,8 @@ mode: "wide"
544
577
-**FixedSizeChunking issue with overlap:** Fixed issue where chunking would fail if overlap was set.
545
578
-**Claude tools with multiple types**: Fixed an issue where Claude tools would break when handling a union of types in parameters.
546
579
-**JSON response parsing**: Fixed cases where JSON model responses returned quoted strings within dictionary values.
547
-
</Update>
580
+
581
+
</Update>
548
582
549
583
<Updatelabel="2025-02-17"description="v1.1.4">
550
584
## 1.1.4
@@ -559,15 +593,17 @@ mode: "wide"
559
593
-**Gemini Safety Parameters**: Fixed an issue with passing safety parameters in Gemini.
560
594
-**ChromaDB Multiple Docs:** Fixed an issue with loading multiple documents into ChromaDB.
561
595
-**Agentic Chunking:** Fixed an issue where OpenAI was required for chunking even when a model was provided.
562
-
</Update>
596
+
597
+
</Update>
563
598
564
599
<Updatelabel="2025-02-16"description="v1.1.3">
565
600
## 1.1.3
566
601
567
602
## Bug Fixes:
568
603
569
604
-**Gemini Tool-Call History**: Fixed an issue where Gemini rejected tool-calls from historic messages.
570
-
</Update>
605
+
606
+
</Update>
571
607
572
608
<Updatelabel="2025-02-15"description="v1.1.2">
573
609
## 1.1.2
@@ -594,7 +630,8 @@ mode: "wide"
594
630
-**Singlestore Fix:** Fixed an issue where querying SingleStore caused the embeddings column to return in binary format.
595
631
-**MongoDB Vectorstore Fix:** Fixed multiple issues in MongoDB, including duplicate creation and deletion of collections during initialization. All known issues have been resolved.
596
632
-**LanceDB Fix:** Fixed various errors in LanceDB and added on_bad_vectors as a parameter.
597
-
</Update>
633
+
634
+
</Update>
598
635
599
636
<Updatelabel="2025-02-14"description="v1.1.1">
600
637
## 1.1.1
@@ -639,7 +676,8 @@ mode: "wide"
639
676
-**MistralEmbedder:** Fixed issue with instantiation of `MistralEmbedder`.
640
677
-**Reasoning**: Fixed an issue with setting reasoning models.
641
678
-**Audio Response:** Fixed an issue with streaming audio artefacts to the playground.
642
-
</Update>
679
+
680
+
</Update>
643
681
644
682
<Updatelabel="2025-02-12"description="v1.1.0">
645
683
## 1.1.0 - Models Refactor and Cloud Support
@@ -705,7 +743,8 @@ mode: "wide"
705
743
## Bug Fixes:
706
744
707
745
-**Retriever as knowledge source**: Added small fix and examples for using the custom `retriever` parameter with an agent.
708
-
</Update>
746
+
747
+
</Update>
709
748
710
749
<Updatelabel="2025-02-05"description="v1.0.6">
711
750
## 1.0.6
@@ -719,7 +758,8 @@ mode: "wide"
719
758
720
759
-**Zoom tools fix:** Zoom tools updated to include the auth step and other misc fixes.
721
760
-**Github search_repositories pagination**: Pagination did not work correctly and this was fixed.
722
-
</Update>
761
+
762
+
</Update>
723
763
724
764
<Updatelabel="2025-02-03"description="v1.0.5">
725
765
## 1.0.5
@@ -733,7 +773,8 @@ mode: "wide"
733
773
-**Exa Toolkit Upgrade:** Added `find_similar` to `ExaTools`
734
774
-**Claude Async:** Claude models can now be used with `await agent.aprint_response()` and `await agent.arun()`.
735
775
-**Mistral Vision:** Mistral vision models are now supported. Various examples were added to illustrate [example](https://github.com/agno-agi/agno/blob/main/cookbook/models/mistral/image_file_input_agent.py).
736
-
</Update>
776
+
777
+
</Update>
737
778
738
779
<Updatelabel="2025-02-02"description="v1.0.4">
739
780
## 1.0.4
@@ -765,15 +806,17 @@ mode: "wide"
765
806
766
807
-**Agent Dataclass Compatibility:** Removed `slots=True` from the agent dataclass decorator, which was not compatible with Python < 3.10.
767
808
-**AzureOpenAIEmbedder:** Made `AzureOpenAIEmbedder` a dataclass to match other embedders.
768
-
</Update>
809
+
810
+
</Update>
769
811
770
812
<Updatelabel="2025-01-31"description="v1.0.1">
771
813
## 1.0.1
772
814
773
815
## Improvement:
774
816
775
817
-**Mistral Model Caching:** Enabled caching for Mistral models.
0 commit comments